© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137756
    Prev
    Next
    INDEX
    Explanations

    combinational logic

    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
    问
    0.59
    I
    0.55
     voraus
    0.55
    걸
    0.55
    ystyrene
    0.54
     solicitudes
    0.53
    력
    0.53
     anemia
    0.52
     muestras
    0.52
    t
    0.52
    POSITIVE LOGITS
    2
    0.61
    4
    0.60
    ក្នុង
    0.59
    8
    0.55
    garh
    0.55
     Carroll
    0.53
    。
    0.52
    чо
    0.51
    HI
    0.51
     Credit
    0.50
    Activations Density 0.001%

    No Known Activations