© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15581
    Prev
    Next
    INDEX
    Explanations

    a jumble of version numbers, identifiers, and other codes

    oai_token-act-pair · gemini-2.0-flash

    Sequencing data and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    5
    -1.84
     five
    -1.46
     Five
    -1.23
     fifth
    -1.23
     cinq
    -1.20
     vijf
    -1.20
     fünf
    -1.16
    five
    -1.16
     cinco
    -1.15
    五
    -1.15
    POSITIVE LOGITS
    writeFieldEnd
    0.84
    DockStyle
    0.78
    awtextra
    0.67
    setVerticalGroup
    0.66
    ResumeLayout
    0.65
     Réponses
    0.59
     يتيمه
    0.57
    دانشنامهٔ
    0.56
     Seventeen
    0.56
     Sixteen
    0.56
    Activations Density 2.675%

    No Known Activations