© 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. 15343
    Prev
    Next
    INDEX
    Explanations

    sentences that contain the word "is"

    oai_token-act-pair · gemini-2.0-flash

    terms related to representation and diversity in media

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

    online content snippets

    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
    gucigalpa
    -0.52
     betweenstory
    -0.49
     umgekehrt
    -0.49
     Objective
    -0.48
    "}")
    -0.48
    blogspot
    -0.47
    ristan
    -0.47
    ToUpdate
    -0.47
    大和
    -0.46
    Kategorie
    -0.46
    POSITIVE LOGITS
    Portale
    0.67
    complexContent
    0.66
     propOrder
    0.65
    Autoritní
    0.64
    شهاد
    0.59
    oredCriteria
    0.57
     something
    0.57
     BoxDecoration
    0.56
     NSCoder
    0.56
     becoming
    0.56
    Activations Density 2.050%

    No Known Activations