© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193474
    Prev
    Next
    INDEX
    Explanations

    asking or seeking dangerous information

    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
    Negative Logits
    language
    0.43
    高中
    0.41
    affect
    0.40
    Affect
    0.39
     Ris
    0.38
     பொருந்த
    0.38
    硝
    0.38
    MATRIX
    0.38
    Signing
    0.38
     Affect
    0.37
    POSITIVE LOGITS
     cats
    0.44
     absorbs
    0.44
     circumst
    0.44
     kucing
    0.44
     fortunately
    0.43
    <unused62>
    0.43
     knew
    0.42
     ['(?
    0.42
    這次
    0.42
     ought
    0.42
    Activations Density 0.019%

    No Known Activations