© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1256
    Prev
    Next
    INDEX
    Explanations

    terms for different kinds of measurements

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    SourceChecksum
    -0.86
     للمعارف
    -0.65
     Infórmanos
    -0.61
     lenker
    -0.58
    таратура
    -0.56
    出版年
    -0.55
     <=",
    -0.54
    Demografie
    -0.54
    disha
    -0.51
    onActivityResult
    -0.50
    POSITIVE LOGITS
    VersionUID
    0.73
     itſelf
    0.62
     Cabello
    0.56
    EndContext
    0.55
    ungkinkan
    0.53
     otur
    0.53
     cauſe
    0.52
     pleaſure
    0.51
     themſelves
    0.51
     ſever
    0.51
    Activations Density 3.130%

    No Known Activations