© 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. 14288
    Prev
    Next
    INDEX
    Explanations

    words spoken in a dialog

    oai_token-act-pair · gemini-2.0-flash

    dialogues

    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
    :].
    -0.65
    ()].
    -0.62
     hỏi
    -0.60
    Autoritní
    -0.57
    ']").
    -0.56
     disambiguazione
    -0.52
    basicConfig
    -0.52
    исленность
    -0.52
    endphp
    -0.51
    "]').
    -0.50
    POSITIVE LOGITS
    ValueStyle
    0.64
    BeginContext
    0.63
     препратки
    0.59
     kasarigan
    0.56
     ویکی‌پدیای
    0.55
    Pautan
    0.55
    ScopeManager
    0.55
    ticello
    0.52
     esternos
    0.51
     typelib
    0.51
    Activations Density 1.113%

    No Known Activations