© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140135
    Prev
    Next
    INDEX
    Explanations

    know how to

    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
    w
    0.73
    ad
    0.67
    ز
    0.56
    ,"
    0.54
     nowych
    0.54
    器的
    0.52
    wrote
    0.52
    up
    0.50
    дии
    0.50
     قوان
    0.50
    POSITIVE LOGITS
    ATIVE
    0.57
    داع
    0.56
    맇
    0.55
    IVATE
    0.54
    RENGTH
    0.52
     goodness
    0.52
     الدع
    0.52
     Sukh
    0.51
    HttpSession
    0.50
    晠
    0.50
    Activations Density 0.001%

    No Known Activations