© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 58860
    Prev
    Next
    INDEX
    Explanations

    click

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    {})
    0.45
     PROBLEM
    0.41
     ದೇ
    0.40
    {-
    0.39
     YE
    0.39
     Chu
    0.38
    {*
    0.37
    [,]
    0.36
     '}
    0.36
    {
    0.35
    POSITIVE LOGITS
    Click
    1.01
     clicking
    0.86
    clicking
    0.77
     Klik
    0.74
     klik
    0.73
    click
    0.71
     clicked
    0.71
    Klik
    0.71
     click
    0.70
     cliquer
    0.70
    Activations Density 0.002%

    No Known Activations