© 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-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24502
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ing
    0.52
    Bits
    0.49
    th
    0.48
    ive
    0.48
    Bush
    0.48
    T
    0.47
    man
    0.46
    sw
    0.46
    not
    0.45
    $).
    0.45
    POSITIVE LOGITS
    ifient
    0.55
    氅
    0.55
     Muitos
    0.53
    зка
    0.52
     Дон
    0.52
     RenderTexture
    0.52
    柬
    0.51
    ੌ
    0.51
    вла
    0.50
    हिमा
    0.50
    Activations Density 0.000%

    No Known Activations