© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11267
    Prev
    Next
    INDEX
    Explanations

    words related to plumbing, DNA sampling, variables, or French locations.

    oai_token-act-pair · gemini-2.0-flash

    drain

    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
    <bos>
    -1.74
    ↵↵
    -1.28
    .
    -1.17
    <eos>
    -1.16
     the
    -1.15
    '
    -1.15
    -
    -1.05
     (
    -1.04
    _
    -1.04
    ,
    -1.02
    POSITIVE LOGITS
     Efq
    2.34
     myſelf
    2.28
     itſelf
    2.06
     Theſe
    1.98
     Houſe
    1.95
     ſeveral
    1.95
     ―――――
    1.92
     Majefty
    1.90
     Jefus
    1.90
     themſelves
    1.88
    Activations Density 1.528%

    No Known Activations