© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46137
    Prev
    Next
    INDEX
    Explanations

    contrast and trim

    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
     "&#
    0.39
     multiport
    0.36
    гій
    0.36
     ""<
    0.35
     IMEI
    0.35
     iot
    0.34
     behe
    0.34
     mex
    0.34
    swagen
    0.33
     spaceShip
    0.33
    POSITIVE LOGITS
    answers
    0.41
    i
    0.38
    at
    0.37
    in
    0.37
    errors
    0.35
    between
    0.35
    as
    0.33
    Chapter
    0.33
    Variables
    0.33
    extraction
    0.33
    Activations Density 0.005%

    No Known Activations