© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 63094
    Prev
    Next
    INDEX
    Explanations

    8

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     suicide
    0.85
     Suicide
    0.80
     suicidal
    0.79
     suic
    0.72
     suicides
    0.65
     आत्महत्या
    0.54
    自殺
    0.53
    苏
    0.46
     আত্মহত্যা
    0.45
     Game
    0.42
    POSITIVE LOGITS
    Mat
    0.58
    Schn
    0.46
    Norm
    0.43
    Erst
    0.43
    Lua
    0.42
    Cit
    0.42
    Tec
    0.42
    Enum
    0.42
    Overlay
    0.42
    Hit
    0.42
    Activations Density 0.001%

    No Known Activations