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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12282
    Prev
    Next
    INDEX
    Explanations

    multi-line quoted sections in emails or forum posts.

    oai_token-act-pair · gemini-2.0-flash

    Forum posts/discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ValueStyle
    -0.72
     ModelExpression
    -0.65
    sizeCache
    -0.65
    writeFieldEnd
    -0.64
    contentLoaded
    -0.63
    <bos>
    -0.62
    >{@
    -0.61
    endregion
    -0.57
    msgTypes
    -0.57
    PMailer
    -0.57
    POSITIVE LOGITS
     télévisée
    0.43
     tục
    0.43
    godic
    0.43
    thyroidism
    0.42
     szolg
    0.42
     touristique
    0.42
    entennial
    0.41
    ragende
    0.41
    Pardon
    0.40
    Diweddarwch
    0.40
    Activations Density 0.386%

    No Known Activations