© 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. 138658
    Prev
    Next
    INDEX
    Explanations

    sexual assault hotline

    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
    strtolower
    0.40
     開
    0.36
    ₄
    0.35
    ించింది
    0.34
    lowercase
    0.34
     下
    0.34
    下載
    0.34
    downcase
    0.34
    🧬
    0.33
     ≥
    0.33
    POSITIVE LOGITS
    渔
    0.48
     lapangan
    0.43
    髀
    0.40
     Trident
    0.40
     Wiesner
    0.38
     visible
    0.38
    퍽
    0.38
     eren
    0.37
     pies
    0.37
     pierre
    0.37
    Activations Density 0.003%

    No Known Activations