© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8965
    Prev
    Next
    INDEX
    Explanations

    words related to manufacturing, medicine, or natural disasters, particularly when used in conjunction with quantities or measurements.

    oai_token-act-pair · gemini-2.0-flash

    implants

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     doInBackground
    -0.71
     Paglinawan
    -0.67
     ModelExpression
    -0.59
     Drapeau
    -0.56
    verwijspagina
    -0.54
    tered
    -0.54
    jsdelivr
    -0.52
     الاطلاع
    -0.51
    oredCriteria
    -0.50
    aarrggbb
    -0.48
    POSITIVE LOGITS
     pacchetto
    0.54
     fieldNum
    0.51
     tund
    0.49
     FetchType
    0.48
    tonode
    0.47
    Lij
    0.47
     réessayer
    0.47
    MockBean
    0.46
     itſelf
    0.46
     Efq
    0.46
    Activations Density 8.310%

    No Known Activations