© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9720
    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_40_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
     overwhelming
    0.37
    jsxFileName
    0.37
    Ri
    0.37
     Ri
    0.37
     extern
    0.37
     Maple
    0.37
     Gaz
    0.36
    茂
    0.36
     Mort
    0.36
     கூடுதலாக
    0.36
    POSITIVE LOGITS
     HMO
    0.39
     naw
    0.38
    Vt
    0.38
    iched
    0.38
    Conversion
    0.38
    ეხ
    0.37
    hst
    0.37
     reli
    0.37
     conversion
    0.36
    ہری
    0.36
    Activations Density 0.025%

    No Known Activations