© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 134941
    Prev
    Next
    INDEX
    Explanations

    selection and data grouping

    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_37_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
     سلاټ
    0.43
    Digits
    0.40
    🎊
    0.40
    rest
    0.39
    रेस्ट
    0.39
     Flu
    0.38
    qr
    0.37
    flox
    0.37
    gif
    0.36
    QR
    0.36
    POSITIVE LOGITS
    摇
    0.42
    [,
    0.41
     kal
    0.40
     bead
    0.39
     columns
    0.38
    [:,
    0.38
    ည်း
    0.38
     inter
    0.38
     incomplete
    0.37
     protocols
    0.36
    Activations Density 0.000%

    No Known Activations