© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257962
    Prev
    Next
    INDEX
    Explanations

    identity function

    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_22_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
    Hight
    0.48
    இதில்
    0.48
    ንግ
    0.43
    υπ
    0.42
     Among
    0.41
    Tous
    0.41
    [,,"
    0.41
     கலைஞ
    0.40
     концерт
    0.40
     بواسط
    0.40
    POSITIVE LOGITS
    津
    0.40
     rte
    0.39
    লো
    0.38
    frey
    0.38
     TPS
    0.38
     lagen
    0.37
     Georges
    0.36
    •
    0.35
     bother
    0.35
    gomery
    0.35
    Activations Density 0.000%

    No Known Activations