© 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. 121643
    Prev
    Next
    INDEX
    Explanations

    friendly matches

    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
    按
    0.39
     genomen
    0.37
    दम
    0.35
     चेन
    0.35
     thôn
    0.35
     আনা
    0.33
     zabez
    0.33
     tenacity
    0.33
     serializers
    0.33
    तम
    0.32
    POSITIVE LOGITS
     Friendly
    0.39
     Doi
    0.36
     Carr
    0.35
    িয়৷
    0.34
    ])*
    0.34
     measuring
    0.34
     Friendship
    0.33
     Amendment
    0.32
     Camp
    0.32
     affiliations
    0.32
    Activations Density 0.000%

    No Known Activations