© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3588
    Prev
    Next
    INDEX
    Explanations

    a hodgepodge of terms from different languages and contexts like code, scientific writing, informal conversation and a web form.

    oai_token-act-pair · gemini-2.0-flash

    unusual text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     שוליים
    -0.87
    esModule
    -0.76
    \{\\
    -0.71
     مشين
    -0.70
    VersionUID
    -0.70
    
    -0.69
     OMITTED
    -0.69
    +:+
    -0.65
    </thead>
    -0.65
    WriteLiteral
    -0.65
    POSITIVE LOGITS
    Autoritní
    0.56
     TextAppearance
    0.49
    bilirsiniz
    0.45
     виправивши
    0.44
    mybatisplus
    0.44
     myſelf
    0.44
     Dernière
    0.43
     badkamer
    0.43
    IMDG
    0.41
     perfons
    0.40
    Activations Density 15.556%

    No Known Activations