© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 241435
    Prev
    Next
    INDEX
    Explanations

    explicitly prohibit

    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
    Negative Logits
     completely
    0.43
    撅
    0.41
     put
    0.39
    屁
    0.39
     totally
    0.39
     complètement
    0.38
     völlig
    0.38
     conceding
    0.37
     butt
    0.36
     같
    0.36
    POSITIVE LOGITS
     Identified
    0.47
     identified
    0.44
    identified
    0.43
     identificar
    0.42
     identificación
    0.42
     identificado
    0.41
     મતદાન
    0.40
     identification
    0.39
     identific
    0.39
     formulations
    0.38
    Activations Density 0.005%

    No Known Activations