© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 221217
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by specific words

    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_31_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
     exiting
    0.38
     insuring
    0.37
     yearning
    0.34
    𝒅
    0.34
     curing
    0.33
     undergoing
    0.33
     pess
    0.33
    льки
    0.33
     completing
    0.33
     hig
    0.33
    POSITIVE LOGITS
    Có
    0.41
    }:=\
    0.36
     Displaystyle
    0.36
     retrouver
    0.35
    结
    0.35
    ʖ
    0.35
     있다면
    0.34
    見る
    0.34
    читься
    0.34
    getSource
    0.34
    Activations Density 0.000%

    No Known Activations