© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61473
    Prev
    Next
    INDEX
    Explanations

    no coding required

    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
    u
    0.68
    ina
    0.68
     "
    0.67
    query
    0.67
    en
    0.66
    uole
    0.65
    o
    0.60
    (
    0.59
    année
    0.59
    pling
    0.59
    POSITIVE LOGITS
     rink
    0.61
     escult
    0.61
     ambition
    0.61
     consoles
    0.60
     faucets
    0.58
     அ
    0.57
     она
    0.57
     serum
    0.56
     malice
    0.56
     blame
    0.56
    Activations Density 0.004%

    No Known Activations