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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14674
    Prev
    Next
    INDEX
    Explanations

    descriptions of crime scenes along with related injuries and objects

    oai_token-act-pair · gemini-2.0-flash

    spatial prepositions and related terms

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

    Damage and markings

    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
    Enllaces
    -0.69
     مشين
    -0.66
    NewUrlParser
    -0.57
    ”?
    -0.57
    因为它
    -0.54
    AntiForgeryToken
    -0.54
    ⁡
    -0.54
     cinquante
    -0.53
     plegable
    -0.53
     itſelf
    -0.53
    POSITIVE LOGITS
     on
    0.73
     under
    0.50
    हास
    0.49
    线上
    0.48
     at
    0.48
    protoimpl
    0.47
     in
    0.46
    نم
    0.44
    cagon
    0.44
     unter
    0.44
    Activations Density 2.994%

    No Known Activations