© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126302
    Prev
    Next
    INDEX
    Explanations

    Route handler

    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_3_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
     practitioner
    0.63
    ată
    0.59
    0.59
    0.55
     repellent
    0.54
    0.53
     be
    0.53
     pixel
    0.52
    с
    0.51
     вой
    0.51
    POSITIVE LOGITS
    Route
    0.76
    न
    0.74
     ROUT
    0.70
    ла
    0.66
    Routes
    0.64
     ROUTES
    0.63
    that
    0.62
     utilisateurs
    0.61
     cargas
    0.61
     Route
    0.60
    Activations Density 0.001%

    No Known Activations