© 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. 232549
    Prev
    Next
    INDEX
    Explanations

    working class

    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
     decidido
    1.09
    価格
    1.09
    もら
    1.09
    {
    1.08
     dupa
    1.02
    রামর্শ
    1.02
     точки
    1.02
    \
    1.01
    İN
    1.00
     années
    0.99
    POSITIVE LOGITS
    r
    1.16
    on
    1.05
    ्
    0.89
     مختلف
    0.88
     konfl
    0.84
    ing
    0.82
     kinship
    0.80
     المختلف
    0.79
    ตำ
    0.79
    BleStatus
    0.78
    Activations Density 0.000%

    No Known Activations