© 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. 205155
    Prev
    Next
    INDEX
    Explanations

    context menu

    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
    ing
    1.23
    us
    1.20
    in
    1.14
    on
    1.05
    :
    1.05
    se
    0.97
     to
    0.96
    ville
    0.96
    le
    0.93
     with
    0.92
    POSITIVE LOGITS
     Tentang
    1.06
     Manajemen
    1.04
     kuhusu
    0.95
    DepartTime
    0.94
    ３
    0.93
     Ответ
    0.91
     Accesat
    0.91
    ４
    0.90
     Ευ
    0.89
     Đáp
    0.89
    Activations Density 0.001%

    No Known Activations