© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 201933
    Prev
    Next
    INDEX
    Explanations

    for loops

    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
    !()
    0.41
     WR
    0.40
    euro
    0.38
    ጋ
    0.37
     paragraph
    0.37
     იგი
    0.37
     HREF
    0.36
     dowol
    0.36
    डाय
    0.36
     reduct
    0.35
    POSITIVE LOGITS
    notFound
    0.37
     estates
    0.37
    "))
    0.36
     eternity
    0.36
    contentInset
    0.35
     हिन्दू
    0.35
     garages
    0.35
    ཎ
    0.35
     programmers
    0.35
     Sloan
    0.35
    Activations Density 0.002%

    No Known Activations