© 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. 12073
    Prev
    Next
    INDEX
    Explanations

    a mix of seemingly unrelated tokens, including the word "got", and tokens related to a specific region

    oai_token-act-pair · 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
    AndEndTag
    -0.94
     pageContext
    -0.85
     useEffect
    -0.82
    tonode
    -0.76
    makeConstraints
    -0.75
    KommentareTeilen
    -0.72
    indd
    -0.72
    CloseOperation
    -0.70
     Dernière
    -0.69
    mybatisplus
    -0.67
    POSITIVE LOGITS
     fenómeno
    0.63
     incele
    0.56
     durumda
    0.55
     типу
    0.52
     kerül
    0.51
     Meier
    0.51
     vardır
    0.50
     Gefahr
    0.50
     kawaida
    0.50
     vlastní
    0.49
    Activations Density 0.152%

    No Known Activations