© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 66308
    Prev
    Next
    INDEX
    Explanations

    non-standard text

    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_51_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
     Speck
    0.41
     Pon
    0.41
     Fuchs
    0.40
    ᱲ
    0.38
     સ્
    0.38
     An
    0.37
    裒
    0.37
     concrete
    0.37
    spe
    0.37
    粨
    0.37
    POSITIVE LOGITS
    urato
    0.38
     Йо
    0.38
    substituted
    0.36
     உத்தர
    0.36
    бира
    0.36
    यद
    0.35
     grammaticality
    0.35
     tetromino
    0.35
     тормо
    0.35
    mtq
    0.34
    Activations Density 0.000%

    No Known Activations