© 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. 2545
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially related to boolean logic and JSON responses

    oai_token-act-pair · gemini-2.0-flash

    special characters and programming syntax

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

    say "false"

    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
    arthed
    -0.56
    ség
    -0.52
    bool
    -0.51
    ukone
    -0.49
    tanooga
    -0.47
    raires
    -0.47
     ick
    -0.47
    لاثة
    -0.47
     bool
    -0.46
     exacte
    -0.46
    POSITIVE LOGITS
     Conſ
    0.63
    EndContext
    0.60
    ⓘ
    0.59
     Roskov
    0.57
     insuffisamment
    0.55
    ագրություններ
    0.55
    ContentAsync
    0.55
    原始内容存档于
    0.54
    TemporalType
    0.54
     مشين
    0.53
    Activations Density 5.526%

    No Known Activations