© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3808
    Prev
    Next
    INDEX
    Explanations

    instances of taking action

    oai_token-act-pair · gemini-2.0-flash

    instructions or actions to take

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

    take

    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
    MigrationBuilder
    -0.80
     Paglinawan
    -0.80
     StatefulWidget
    -0.69
    VersionUID
    -0.64
    UserScript
    -0.60
    chelles
    -0.56
     aDecoder
    -0.55
    LookAnd
    -0.55
    Referencer
    -0.53
     defaultstate
    -0.52
    POSITIVE LOGITS
    لاعب
    0.57
    KURZBESCHREIBUNG
    0.54
     bæ
    0.53
    stylers
    0.53
     significant
    0.53
    vacy
    0.53
    holdings
    0.53
    根本
    0.49
     into
    0.48
     positive
    0.48
    Activations Density 1.113%

    No Known Activations