© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43142
    Prev
    Next
    INDEX
    Explanations

    rnbqkbnr

    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
    u
    0.78
    as
    0.72
    i
    0.70
     superficially
    0.70
     growths
    0.70
    iiv
    0.68
     пациен
    0.67
     lié
    0.66
    I
    0.65
    త
    0.64
    POSITIVE LOGITS
    OP
    0.82
    ри
    0.81
    c
    0.72
    g
    0.72
    לי
    0.71
    UT
    0.71
    е
    0.71
    ק
    0.71
    اني
    0.68
    ون
    0.68
    Activations Density 0.002%

    No Known Activations