© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197404
    Prev
    Next
    INDEX
    Explanations

    Spencer Communications

    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_4_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
    1
    1.13
    an
    1.13
    as
    1.09
    ان
    0.95
    는
    0.95
    是
    0.91
    in
    0.91
    は
    0.83
    ig
    0.82
    ین
    0.82
    POSITIVE LOGITS
     yapt
    0.95
    もちろん
    0.93
     yaptığı
    0.86
    犸
    0.86
    м
    0.83
     tentunya
    0.82
     ﺍﻟ
    0.81
    ğ
    0.80
     îl
    0.80
     grouse
    0.79
    Activations Density 0.000%

    No Known Activations