© 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. 40245
    Prev
    Next
    INDEX
    Explanations

    talking points

    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
    ře
    0.63
    iß
    0.63
    čku
    0.62
    kaar
    0.62
    нами
    0.61
    يمي
    0.59
    ൮
    0.59
    භාව
    0.58
    芷
    0.58
    ikko
    0.57
    POSITIVE LOGITS
    O
    0.67
     accompan
    0.58
    pointed
    0.56
    rated
    0.54
     comprised
    0.54
     mentioned
    0.54
     succinct
    0.54
     eloquent
    0.54
    েলি
    0.53
     editorial
    0.52
    Activations Density 0.004%

    No Known Activations