© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4786
    Prev
    Next
    INDEX
    Explanations

    technical documentation and code, paying special attention to font names and tire construction.

    oai_token-act-pair · gemini-2.0-flash

    Text and tire specifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    fml
    -0.56
    awaiter
    -0.56
     BorderRadius
    -0.52
     Autorizaciones
    -0.52
    CreateModel
    -0.52
     AppDelegate
    -0.52
    coroutines
    -0.50
    DotNetBar
    -0.49
    LayoutConstraint
    -0.48
     Cage
    -0.48
    POSITIVE LOGITS
     **/
    0.62
     Pirelli
    0.56
    ')],
    0.54
     Prim
    0.54
     kaynağından
    0.53
     الاطلاع
    0.53
    <bos>
    0.52
    })`
    0.50
    ')")
    0.49
     movers
    0.49
    Activations Density 0.940%

    No Known Activations