© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 65946
    Prev
    Next
    INDEX
    Explanations

    attack damage

    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_41_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
     creep
    0.70
     creeps
    0.68
     CS
    0.58
    creep
    0.53
    Preprocessor
    0.52
    Last
    0.50
    CSS
    0.50
    农
    0.50
    CS
    0.50
     farm
    0.49
    POSITIVE LOGITS
     Window
    0.38
     asi
    0.38
    ‑
    0.38
    cob
    0.38
    ర్చి
    0.37
     cob
    0.36
     "@
    0.36
     Methyl
    0.36
    ashi
    0.36
     reads
    0.35
    Activations Density 0.004%

    No Known Activations