© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 178216
    Prev
    Next
    INDEX
    Explanations

    03

    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_29_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
     messes
    0.40
     nă
    0.37
     &/
    0.37
    ْل
    0.36
     large
    0.36
     poświę
    0.34
     gă
    0.34
    蘑
    0.34
     कॉलेजों
    0.33
     crevices
    0.33
    POSITIVE LOGITS
    dek
    0.42
     SwiftUI
    0.41
    িতা
    0.41
    ურთიერთ
    0.40
    fx
    0.40
     परिस्थित
    0.40
    ス
    0.40
    オー
    0.39
    quando
    0.39
    IDENT
    0.38
    Activations Density 0.000%

    No Known Activations