© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11761
    Prev
    Next
    INDEX
    Explanations

    programming code snippets and posting metadata

    oai_token-act-pair · gemini-2.0-flash

    Edited post or console output

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    expandindo
    -1.02
     препратки
    -0.88
    }{*}{}
    -0.87
     فريبيس
    -0.82
    PMailer
    -0.81
     onCancelled
    -0.78
    UserScript
    -0.77
    FieldBuilder
    -0.77
     שוליים
    -0.76
     дописавши
    -0.75
    POSITIVE LOGITS
    <bos>
    0.68
    .
    0.68
    ↵
    0.57
    ↵↵
    0.52
    \
    0.47
    Oh
    0.46
     run
    0.44
     off
    0.43
    Run
    0.42
    FormatException
    0.42
    Activations Density 0.708%

    No Known Activations