© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231870
    Prev
    Next
    INDEX
    Explanations

    wiggly or squiggly lines

    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_6_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
    '
    1.45
    e
    1.10
    i
    1.06
    o
    1.02
    han
    1.01
    lık
    0.98
    infile
    0.98
    lig
    0.97
    gün
    0.95
    gra
    0.91
    POSITIVE LOGITS
    S
    1.22
    يا
    1.16
    ER
    1.15
    ST
    1.12
     ancienne
    1.07
    ش
    1.05
    사
    1.05
    وا
    1.03
    R
    1.03
    শ
    1.03
    Activations Density 0.000%

    No Known Activations