© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215011
    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_5_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
    ON
    1.10
    and
    0.99
    ブ
    0.99
     Když
    0.98
    امي
    0.96
    <0x0D>
    0.95
    行う
    0.94
     Allerdings
    0.91
    ó
    0.87
    _
    0.86
    POSITIVE LOGITS
    ش
    1.09
    기
    1.00
    ва
    0.97
    eliness
    0.97
    ರುವ
    0.96
    h
    0.95
    electric
    0.90
    ان
    0.85
    adhesive
    0.84
    creational
    0.81
    Activations Density 0.000%

    No Known Activations