© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12749
    Prev
    Next
    INDEX
    Explanations

    explicitly prohibit or describe harmful content

    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_13_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
    ᱘
    0.68
     irritable
    0.66
    俦
    0.64
     चिंतित
    0.61
     답변
    0.59
     needing
    0.58
    gust
    0.57
     mishaps
    0.56
    िश्चित
    0.56
    덟
    0.55
    POSITIVE LOGITS
     on
    0.63
    on
    0.62
     explicitly
    0.56
     Eden
    0.52
    Eden
    0.50
     explicit
    0.47
     nascost
    0.47
    itz
    0.47
     স্ট
    0.47
     According
    0.46
    Activations Density 0.066%

    No Known Activations