© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76305
    Prev
    Next
    INDEX
    Explanations

    during file processing errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
    เจอ
    0.40
    имость
    0.38
     یافت
    0.38
     userRoutes
    0.38
    식
    0.38
    ᑕ
    0.37
    ക്കാല
    0.36
     overflow
    0.36
    Dimensions
    0.36
    詎
    0.36
    POSITIVE LOGITS
     ಮನ
    0.42
    ambilan
    0.42
    antip
    0.39
    hex
    0.38
     Josephine
    0.36
    øk
    0.36
     hacerlo
    0.36
    囹
    0.35
    функ
    0.35
    таж
    0.35
    Activations Density 0.002%

    No Known Activations