© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 119511
    Prev
    Next
    INDEX
    Explanations

    explosions danger

    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_38_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
     filth
    0.53
     filthy
    0.53
    汚
    0.51
     dirty
    0.45
    Dirty
    0.43
    風險
    0.41
    dirty
    0.40
    Risk
    0.39
     risk
    0.39
    Dirt
    0.38
    POSITIVE LOGITS
    azed
    0.42
     rune
    0.40
    维护
    0.40
     mantuvo
    0.38
    🌝
    0.38
     rie
    0.38
     reine
    0.37
     hemoglobin
    0.37
    alls
    0.37
    scopic
    0.37
    Activations Density 0.019%

    No Known Activations