© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 36436
    Prev
    Next
    INDEX
    Explanations

    quantifying metrics

    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_50_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
     amphithe
    0.36
    <%
    0.36
    ostridium
    0.35
    <<<
    0.34
    ިޔ
    0.32
     prim
    0.32
     «
    0.32
     ¡
    0.31
     %[
    0.31
     সুভাষ
    0.31
    POSITIVE LOGITS
     व्ह
    0.44
     الو
    0.43
    rVert
    0.42
    ウィ
    0.40
    wxT
    0.40
    Wt
    0.40
     Уи
    0.38
    𝗪
    0.38
    Vt
    0.38
    mW
    0.38
    Activations Density 0.610%

    No Known Activations