© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15258
    Prev
    Next
    INDEX
    Explanations

    positive adjectives modifying literature or other creative output, especially when they end in "ly".

    oai_token-act-pair · gemini-2.0-flash

    adjectives describing impactful writing

    np_token-act-pair-logits · gpt-4o-mini

    book reviews

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Réponses
    -0.70
    tagHelperRunner
    -0.67
    TintMode
    -0.66
    DATABASES
    -0.64
    StoryboardSegue
    -0.60
    WebElementEntity
    -0.59
     convertView
    -0.58
     actionMode
    -0.57
     Administrativna
    -0.56
     MaterialApp
    -0.55
    POSITIVE LOGITS
     onderhoud
    0.53
     enriching
    0.52
     engaging
    0.47
     captivating
    0.45
     warm
    0.45
     Bedarf
    0.45
     arresting
    0.44
     eloquent
    0.44
    كويكب
    0.44
     informed
    0.44
    Activations Density 1.094%

    No Known Activations