© 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. 90506
    Prev
    Next
    INDEX
    Explanations

    chasing down whites

    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
     க்கு
    0.68
    ^{*}$.
    0.61
    ၃
    0.61
    ⊡
    0.61
    は
    0.59
    盪
    0.59
     တော့
    0.59
     mél
    0.58
    ické
    0.58
    発生
    0.58
    POSITIVE LOGITS
    f
    0.71
    </h2>
    0.65
    one
    0.63
    A
    0.63
    Employer
    0.62
    F
    0.61
    con
    0.61
    ')
    0.61
    te
    0.59
    ari
    0.57
    Activations Density 0.001%

    No Known Activations