© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38832
    Prev
    Next
    INDEX
    Explanations

    level and job focus

    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_11_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
    t
    0.55
    Alexis
    0.45
     Prés
    0.45
    Fitting
    0.44
    Than
    0.44
     Chirurgien
    0.43
    Grazie
    0.43
    kia
    0.43
    chers
    0.42
    я
    0.42
    POSITIVE LOGITS
     stored
    0.47
     sealant
    0.47
     has
    0.45
     mã
    0.45
     could
    0.44
     somewhat
    0.44
     curricula
    0.44
    ront
    0.43
     how
    0.43
     rRNA
    0.43
    Activations Density 0.034%

    No Known Activations