© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117664
    Prev
    Next
    INDEX
    Explanations

    she began

    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_27_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
     Substituting
    0.39
     Sicherheit
    0.38
     SUBSTIT
    0.37
     سیاه
    0.35
     نتیجه
    0.35
    Substituting
    0.34
     ಕೇಳ
    0.33
    澀
    0.33
    lungen
    0.33
    滑
    0.33
    POSITIVE LOGITS
    istic
    0.33
     surtout
    0.31
     regions
    0.31
     log
    0.30
    SS
    0.30
    pth
    0.30
     efficiency
    0.30
     cheers
    0.29
     crews
    0.29
     prou
    0.29
    Activations Density 0.000%

    No Known Activations