© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 77240
    Prev
    Next
    INDEX
    Explanations

    harm, assassination, sabotage

    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_31_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
    सैन
    0.38
    郯
    0.38
     rescuing
    0.35
     Rescue
    0.35
     neurologic
    0.35
    Neu
    0.35
     түр
    0.35
    穸
    0.35
    𐰆
    0.35
    ោយ
    0.34
    POSITIVE LOGITS
     potions
    0.40
     প্রতিহিংস
    0.38
    substr
    0.38
    }^{+}$
    0.37
     Flats
    0.36
    Wings
    0.36
     wronged
    0.36
     venge
    0.35
     clog
    0.35
     DK
    0.34
    Activations Density 0.074%

    No Known Activations