© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 138890
    Prev
    Next
    INDEX
    Explanations

    options, menu paths, tools

    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_12_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
    sa
    0.32
    ga
    0.29
    light
    0.29
    &
    0.29
    cation
    0.28
    gl
    0.27
    Health
    0.27
    .<
    0.26
    #.
    0.26
    fa
    0.26
    POSITIVE LOGITS
    тая
    0.25
    즈
    0.25
     condesc
    0.24
    畛
    0.24
     conceded
    0.23
     Коми
    0.23
    율
    0.23
     MILLER
    0.23
     ۲۰
    0.23
     conceding
    0.23
    Activations Density 0.000%

    No Known Activations