© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 121295
    Prev
    Next
    INDEX
    Explanations

    indicating a song chorus

    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_37_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
     riječ
    0.37
    そらく
    0.36
     صفحۀ
    0.35
     grandeza
    0.35
    ्यादा
    0.35
    :"",
    0.35
     ribonucle
    0.35
    迪士尼
    0.34
    ()<<"
    0.34
    \":
    0.34
    POSITIVE LOGITS
     repeat
    0.44
     반복
    0.43
     Scholars
    0.42
     alternate
    0.41
     Repeat
    0.41
     scholars
    0.40
     Apply
    0.39
     apply
    0.38
    Repeat
    0.38
     SPR
    0.38
    Activations Density 0.003%

    No Known Activations