© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5562
    Prev
    Next
    INDEX
    Explanations

    positive adjectives and associated words of degree

    oai_token-act-pair · gemini-2.0-flash

    words starting with 'a'

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

    a

    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
    Люди
    -0.59
    SharedCtor
    -0.57
     Cytometry
    -0.57
    Handlung
    -0.56
    __":
    -0.55
    vestres
    -0.54
     oprot
    -0.53
     religieuses
    -0.52
    __':
    -0.52
    icleta
    -0.52
    POSITIVE LOGITS
    OGND
    0.63
     ExecuteAsync
    0.62
    دانشنامهٔ
    0.54
     believer
    0.54
     disponibilités
    0.51
    hasMoreElements
    0.50
     supporter
    0.50
    RectangleBorder
    0.49
    setVerticalGroup
    0.49
     champ
    0.48
    Activations Density 0.812%

    No Known Activations