© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 241867
    Prev
    Next
    INDEX
    Explanations

    health and safety

    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_40_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
    කාර
    0.38
     enablement
    0.38
    섀
    0.37
    නු
    0.36
    lès
    0.36
     infusions
    0.35
     inset
    0.34
     societ
    0.34
    腹
    0.34
    junit
    0.34
    POSITIVE LOGITS
     Hazardous
    0.40
    Training
    0.39
     Muff
    0.38
     சம்ப
    0.38
     அதிச
    0.38
     المشار
    0.37
    匏
    0.37
    hazardous
    0.37
     Hazard
    0.37
     Training
    0.36
    Activations Density 0.002%

    No Known Activations