© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 134223
    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_37_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
    '>"+
    0.40
    tin
    0.40
    atica
    0.38
     gouver
    0.38
    getPage
    0.38
     हल
    0.37
     stirrer
    0.37
    screen
    0.36
     depre
    0.36
     バス
    0.36
    POSITIVE LOGITS
     daging
    0.40
     Kxh
    0.37
    を感じ
    0.35
    腥
    0.34
     thirteen
    0.34
    剜
    0.34
    WV
    0.34
    коменду
    0.34
    ᠨ
    0.33
     rém
    0.33
    Activations Density 0.000%

    No Known Activations