© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 194106
    Prev
    Next
    INDEX
    Explanations

    memorize

    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_4_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
     on
    1.27
    ik
    1.09
    ت
    0.98
    im
    0.88
    elor
    0.87
    </h2>
    0.85
    il
    0.85
    S
    0.83
    ikko
    0.82
    em
    0.80
    POSITIVE LOGITS
    ।
    0.99
    ský
    0.93
    ב
    0.89
    एफ
    0.86
    deki
    0.82
    ير
    0.80
    0.80
    يش
    0.77
    дагы
    0.76
    да
    0.75
    Activations Density 0.002%

    No Known Activations