© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43394
    Prev
    Next
    INDEX
    Explanations

    fractional, integer, updates

    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_13_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
    koz
    0.48
     correlation
    0.45
    ur
    0.45
     propag
    0.45
    ON
    0.45
     r
    0.44
     RPG
    0.44
    uhan
    0.43
     liber
    0.43
     gest
    0.43
    POSITIVE LOGITS
    ineries
    0.54
     وسط
    0.51
     ஏழு
    0.48
     kesk
    0.47
     באמצע
    0.47
     ܒ
    0.46
    Istanbul
    0.44
    SIBILITIES
    0.43
     مشینیں
    0.43
     Ecusson
    0.43
    Activations Density 0.002%

    No Known Activations