© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 34408
    Prev
    Next
    INDEX
    Explanations

    you've hit on a

    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_7_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
    o
    1.02
    ש
    0.95
    した
    0.79
    an
    0.77
     a
    0.75
    ール
    0.74
    ָד
    0.74
     can
    0.71
    する
    0.71
    ul
    0.71
    POSITIVE LOGITS
    4
    0.84
    ل
    0.75
    ،
    0.70
     وإ
    0.66
    大
    0.64
    3
    0.63
    F
    0.60
    8
    0.60
    7
    0.60
    }")
    0.59
    Activations Density 0.006%

    No Known Activations