© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 256524
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
     tội
    1.26
    <0x80>
    1.22
     शेड्यूल
    1.13
     sudden
    1.10
     sanguí
    1.09
    AsString
    1.08
    istic
    1.08
     ы
    1.05
    igrams
    1.04
     поту
    1.04
    POSITIVE LOGITS
    ी
    1.30
    𠃊
    1.29
    ନ୍ତି
    1.29
    чә
    1.27
    కి
    1.23
     copolymers
    1.19
     CONTRIBUT
    1.09
    ১
    1.09
    মূলক
    1.08
    ся
    1.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.