© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 127424
    Prev
    Next
    INDEX
    Explanations

    actions pose risks or irreversible 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_37_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
    素
    0.41
    izable
    0.38
    pon
    0.37
    晛
    0.37
     זיי
    0.36
    clickable
    0.36
    Iterator
    0.36
    笽
    0.36
     제곱
    0.36
    hpp
    0.35
    POSITIVE LOGITS
     magical
    0.41
     ময়মনসিংহ
    0.39
     meritorious
    0.38
     nemoc
    0.37
    आरटी
    0.37
     رأ
    0.37
     glycol
    0.36
    漉
    0.36
    getMetering
    0.36
     मूर्ति
    0.36
    Activations Density 0.002%

    No Known Activations