© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12557
    Prev
    Next
    INDEX
    Explanations

    the word "most"

    oai_token-act-pair · gemini-2.0-flash

    Business/Economic topics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    tagHelperRunner
    -0.81
    AlterField
    -0.74
    ChildScrollView
    -0.71
    󠁴
    -0.71
    rizona
    -0.70
    ^(@)
    -0.69
     HasFactory
    -0.69
    bootstrapcdn
    -0.69
    astéroïdes
    -0.68
     Профиль
    -0.68
    POSITIVE LOGITS
    BeginContext
    0.52
    po
    0.47
    pas
    0.46
    entera
    0.46
     sva
    0.45
    paan
    0.44
    pa
    0.44
     E
    0.43
     H
    0.43
     performance
    0.43
    Activations Density 1.968%

    No Known Activations