© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116153
    Prev
    Next
    INDEX
    Explanations

    harm or danger to self or others

    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_27_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
     TypeToken
    0.41
    收益
    0.41
    对我
    0.41
    STRUCTION
    0.40
     संख्याओं
    0.38
     дохода
    0.38
    崑
    0.37
     imani
    0.37
     մի
    0.37
    我现在
    0.37
    POSITIVE LOGITS
     troubled
    0.40
     downgraded
    0.38
     dimmed
    0.35
     warned
    0.34
     harmed
    0.34
     helmet
    0.34
     unsuspecting
    0.33
    髅
    0.33
     impaired
    0.33
     auctioned
    0.33
    Activations Density 0.008%

    No Known Activations