© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15008
    Prev
    Next
    INDEX
    Explanations

    adverbs related to time and verbs related to recognition or accomplishment

    oai_token-act-pair · gemini-2.0-flash

    immediately or awarded

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    -0.83
    AccessorTable
    -0.77
    WebpackPlugin
    -0.77
    EndGlobalSection
    -0.75
     SPOILERS
    -0.75
    TimerTask
    -0.71
    HomeAsUp
    -0.71
    UnknownFieldSet
    -0.71
    celotti
    -0.70
    WarningLevel
    -0.69
    POSITIVE LOGITS
    <bos>
    0.65
     lâng
    0.64
     
    0.61
     Nacionales
    0.60
    s
    0.57
    cluye
    0.57
     alábbi
    0.57
     antaranya
    0.57
     låg
    0.56
     høre
    0.56
    Activations Density 0.613%

    No Known Activations