© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 207900
    Prev
    Next
    INDEX
    Explanations

    Russian endings

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     Wiesner
    0.37
    Dash
    0.35
    irish
    0.35
     مصنوعی
    0.34
    펫
    0.34
    night
    0.34
    archer
    0.34
    atlan
    0.34
     Pane
    0.34
     Chel
    0.34
    POSITIVE LOGITS
    лых
    0.82
    лый
    0.80
    лые
    0.77
    лую
    0.69
    лыми
    0.68
    лая
    0.65
    лое
    0.61
    лой
    0.60
    лого
    0.58
    い
    0.58
    Activations Density 0.001%

    No Known Activations