© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 83452
    Prev
    Next
    INDEX
    Explanations

    ax^2 + bx + c

    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_29_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
     कथित
    0.38
    étr
    0.35
    Alleg
    0.35
    argsort
    0.34
    獨
    0.34
    癖
    0.34
    Consistent
    0.34
    Reward
    0.34
    empirical
    0.34
    不满
    0.33
    POSITIVE LOGITS
    ନା
    0.40
    炘
    0.40
     compose
    0.39
     insist
    0.38
     circumcision
    0.38
     alumina
    0.38
     மெட்ரோ
    0.38
     masculin
    0.38
     নিকটে
    0.38
    정을
    0.37
    Activations Density 0.000%

    No Known Activations