© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 205759
    Prev
    Next
    INDEX
    Explanations

    technical instructions

    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_46_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
    язку
    0.42
    payable
    0.36
    nis
    0.34
    drawiam
    0.33
     â
    0.33
    ियाँ
    0.33
    sthe
    0.33
    ſon
    0.32
     základě
    0.32
    cedures
    0.32
    POSITIVE LOGITS
    ؛
    0.54
    而已
    0.48
    ;
    0.48
    嗎
    0.47
     ಎಂದು
    0.45
     کیونکہ
    0.45
    ?—
    0.45
    $;
    0.44
    吗
    0.44
    ?;
    0.44
    Activations Density 0.137%

    No Known Activations