© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46041
    Prev
    Next
    INDEX
    Explanations

    primary driver, focus, or source

    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_13_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
    C
    0.29
     कैरी
    0.28
     παιδιά
    0.28
    残留
    0.27
     Succession
    0.27
    N
    0.27
     Residual
    0.27
     Kindern
    0.26
    ร
    0.26
     Same
    0.25
    POSITIVE LOGITS
     номе
    0.27
     Верхов
    0.26
    え
    0.26
    ovali
    0.25
    pesar
    0.25
    ҷи
    0.25
    কুট
    0.25
    ovina
    0.25
    moja
    0.24
    URUK
    0.24
    Activations Density 0.017%

    No Known Activations