© 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. 178541
    Prev
    Next
    INDEX
    Explanations

    own

    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
    秃
    0.37
    アク
    0.36
     ак
    0.36
    Often
    0.35
    ্
    0.35
    ँ
    0.34
     Ack
    0.34
    ń
    0.34
     Phenomenology
    0.34
    FACTOR
    0.34
    POSITIVE LOGITS
    absolute
    0.53
    omaly
    0.41
    atibus
    0.39
    attuale
    0.39
    stitute
    0.39
    িয়োগ
    0.39
     utter
    0.39
     mischief
    0.39
    rue
    0.38
    شاء
    0.38
    Activations Density 0.002%

    No Known Activations