© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 177910
    Prev
    Next
    INDEX
    Explanations

    compares topics or information from multiple sources

    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_29_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
    按钮
    0.30
     reintroduced
    0.30
    󰀄
    0.29
    discount
    0.29
    Servo
    0.29
    溅
    0.29
    绺
    0.29
    RMSE
    0.29
     servo
    0.29
    收获
    0.29
    POSITIVE LOGITS
     tribulations
    0.35
     Rose
    0.32
     Proposition
    0.32
     ass
    0.32
     ROSE
    0.32
     Letter
    0.31
     Z
    0.31
     trials
    0.31
     sons
    0.31
     Q
    0.31
    Activations Density 0.000%

    No Known Activations