© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 58002
    Prev
    Next
    INDEX
    Explanations

    multiple languages and topics

    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_59_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
     fra
    0.46
    Fra
    0.41
    ദി
    0.41
    fra
    0.40
     hustle
    0.39
    樎
    0.38
     parvenir
    0.37
    燥
    0.37
    Online
    0.37
    Panasonic
    0.37
    POSITIVE LOGITS
     ¿
    0.45
    ¿
    0.45
     ¡
    0.43
    ´
    0.42
     Rá
    0.41
     soz
    0.41
     ´
    0.39
     ún
    0.39
     Of
    0.38
    ¡
    0.38
    Activations Density 0.000%

    No Known Activations