© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13680
    Prev
    Next
    INDEX
    Explanations

    percentage values

    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_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
     percent
    0.78
     %
    0.76
     %,
    0.72
     procent
    0.69
    Percent
    0.68
     %),
    0.68
     prosent
    0.67
    percent
    0.67
    百
    0.65
     %.
    0.64
    POSITIVE LOGITS
    AMSUNG
    0.38
    deletion
    0.36
     пау
    0.36
     착
    0.36
     इम्मेडिएटली
    0.35
     persuade
    0.34
     oauth
    0.34
    ahrung
    0.33
    Unless
    0.33
     অধ্য
    0.33
    Activations Density 0.106%

    No Known Activations