© 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. 75330
    Prev
    Next
    INDEX
    Explanations

    forecasting and alerts

    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
    planetary
    0.38
    Commod
    0.34
     noticeably
    0.33
     MICHIGAN
    0.32
     earth
    0.32
     commodity
    0.32
    Notify
    0.32
     ა
    0.32
     notably
    0.32
     Commodity
    0.31
    POSITIVE LOGITS
    याल
    0.34
    鯊
    0.33
    圆
    0.32
     quanto
    0.32
    anke
    0.32
    ilites
    0.31
     penilaian
    0.31
     runde
    0.31
     aviones
    0.31
    ORTS
    0.31
    Activations Density 0.007%

    No Known Activations