© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 248645
    Prev
    Next
    INDEX
    Explanations

    say "ๆ" phrase

    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_56_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
    -
    0.42
    :$
    0.39
    :
    0.39
    heh
    0.39
    egraphics
    0.38
    stens
    0.37
    ху
    0.37
    (=
    0.37
    mg
    0.36
    ($
    0.36
    POSITIVE LOGITS
    们
    1.02
    們
    1.02
    们的
    0.86
    들도
    0.83
    들에
    0.83
    들을
    0.79
     ๆ
    0.77
    들이
    0.75
    들은
    0.73
    들의
    0.73
    Activations Density 0.000%

    No Known Activations