© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1315
    Prev
    Next
    INDEX
    Explanations

    references to the Arizona Health Care Cost Containment System (AHCCCS)

    oai_token-act-pair · gemini-2.0-flash

    CS

    np_max-act · gemini-2.0-flash

    ends with s

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    featureID
    -0.91
    tvguidetime
    -0.83
    NewUrlParser
    -0.78
    SocketChannel
    -0.77
    lgari
    -0.77
    AsUp
    -0.76
    WireFormatLite
    -0.76
    دانشنامهٔ
    -0.74
     Drapeau
    -0.73
     SqlParameter
    -0.73
    POSITIVE LOGITS
    riss
    0.68
    udas
    0.54
    ACES
    0.50
    innis
    0.48
    EES
    0.48
    VAS
    0.46
     Mess
    0.46
    WGS
    0.46
     Eis
    0.46
    ulis
    0.46
    Activations Density 1.635%

    No Known Activations