© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82186
    Prev
    Next
    INDEX
    Explanations

    explicit sexual content

    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_53_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
     किए
    0.38
    </strong>
    0.37
     लगाए
    0.37
    о
    0.36
     মণ
    0.35
    ‌
    0.35
    </code>
    0.35
     chờ
    0.34
    #[
    0.34
         
    0.34
    POSITIVE LOGITS
     waterproofing
    0.36
    かなか
    0.35
    രുന്നു
    0.35
    െങ്കില്‍
    0.35
     escol
    0.35
    埛
    0.35
    궪
    0.34
     moisturizing
    0.34
     மேற்பட்ட
    0.34
    મ્પ
    0.34
    Activations Density 0.743%

    No Known Activations