© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11742
    Prev
    Next
    INDEX
    Explanations

    names and affiliations

    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_40_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
    iegen
    0.41
     GV
    0.41
    "))
    0.37
     فرمان
    0.36
    差
    0.36
     يعتبر
    0.36
     GCD
    0.36
     Engine
    0.36
    ')),
    0.36
    gung
    0.36
    POSITIVE LOGITS
    ウント
    0.41
     potuto
    0.39
    insch
    0.37
    ẃ
    0.36
    Estim
    0.35
    Honor
    0.35
    Notice
    0.35
    Consulta
    0.35
    重視
    0.35
    ριο
    0.35
    Activations Density 0.008%

    No Known Activations