© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90633
    Prev
    Next
    INDEX
    Explanations

    AUTO_INCREMENT

    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_3_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
    ש
    0.78
    -
    0.71
    ка
    0.71
     sayıda
    0.70
     lahko
    0.69
    ו
    0.69
    া
    0.68
     durumda
    0.67
     relentlessly
    0.67
     has
    0.66
    POSITIVE LOGITS
    of
    0.89
    p
    0.82
    k
    0.73
    n
    0.61
     It
    0.60
    ANN
    0.60
     Ironically
    0.58
    ות
    0.58
     Increases
    0.57
     ک
    0.56
    Activations Density 0.000%

    No Known Activations