© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11833
    Prev
    Next
    INDEX
    Explanations

    terms preceded by "over-" or "under-"

    oai_token-act-pair · gemini-2.0-flash

    over

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     CURLOPT
    -0.70
     FetchType
    -0.68
     overrun
    -0.66
     VizieR
    -0.64
     HttpServlet
    -0.63
     saites
    -0.63
    URLException
    -0.63
     noqa
    -0.61
     trow
    -0.61
     ModelExpression
    -0.61
    POSITIVE LOGITS
     مواليد
    0.55
    !*\
    0.54
    Lähteet
    0.47
    líben
    0.47
    stateParams
    0.46
     here
    0.46
     hierdie
    0.45
    россий
    0.45
    omed
    0.44
    jugend
    0.42
    Activations Density 3.099%

    No Known Activations