© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 51111
    Prev
    Next
    INDEX
    Explanations

    bracket or parenthesized text

    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_10_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
    ل
    0.91
    it
    0.89
    ie
    0.88
    ley
    0.86
    م
    0.86
    ert
    0.85
    asis
    0.83
    z
    0.83
    ers
    0.82
    yo
    0.81
    POSITIVE LOGITS
     Primeiro
    0.75
     Qualquer
    0.73
    前記
    0.71
     Página
    0.71
     Philosophie
    0.70
     Unterstüt
    0.70
     因為
    0.68
     Vân
    0.68
     Continuando
    0.68
     Sprachen
    0.68
    Activations Density 0.000%

    No Known Activations