© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 198238
    Prev
    Next
    INDEX
    Explanations

    australia states house currency

    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_9_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
    簫
    0.52
     jaunâtre
    0.51
    грева
    0.50
     typos
    0.49
     basaltes
    0.48
    ॉग
    0.48
     quotients
    0.48
    ੁੰ
    0.47
    бах
    0.47
     pirm
    0.47
    POSITIVE LOGITS
     an
    0.83
    on
    0.83
    ?
    0.80
    t
    0.73
    <h2>
    0.72
    </h2>
    0.69
    P
    0.69
     andere
    0.69
     will
    0.68
    !
    0.68
    Activations Density 0.000%

    No Known Activations