© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5992
    Prev
    Next
    INDEX
    Explanations

    discourse about movie success or domination

    oai_token-act-pair · gemini-2.0-flash

    box/boxes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     فريبيس
    -0.94
    complexContent
    -0.93
    migrationBuilder
    -0.86
    CopyWith
    -0.81
    PMailer
    -0.77
    EndContext
    -0.77
     Signalez
    -0.75
    parsedMessage
    -0.75
    يكب
    -0.75
    évaluateur
    -0.73
    POSITIVE LOGITS
     box
    1.30
     Box
    1.11
    box
    1.10
    Box
    1.03
     BOX
    0.92
    BOX
    0.90
    boxes
    0.80
     caja
    0.80
     boxes
    0.76
     boxed
    0.74
    Activations Density 0.611%

    No Known Activations