© 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. 195755
    Prev
    Next
    INDEX
    Explanations

    of

    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
    늡
    0.40
    <unused215>
    0.37
    తున్నాయి
    0.37
     становника
    0.36
    ismar
    0.36
     годах
    0.36
     coasters
    0.36
    ieszcz
    0.36
     filosóf
    0.36
    Meth
    0.35
    POSITIVE LOGITS
    be
    0.46
    zo
    0.45
    bes
    0.43
     А
    0.40
    Be
    0.39
    rogram
    0.39
    pix
    0.39
    seo
    0.39
    beta
    0.38
    SEO
    0.37
    Activations Density 0.000%

    No Known Activations