© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7093
    Prev
    Next
    INDEX
    Explanations

    zip / bz compression

    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
    Not in Any Lists

    No Comments

    Negative Logits
    theorem
    0.39
    LaTeX
    0.39
    稅
    0.38
     sucedido
    0.37
    ণী
    0.36
    ティー
    0.36
     غم
    0.36
     planilla
    0.36
     ද
    0.36
     fonction
    0.35
    POSITIVE LOGITS
     Commentary
    0.54
     commentary
    0.45
     urgency
    0.41
    Comment
    0.40
     parallel
    0.38
     Lightfoot
    0.38
     Kommentar
    0.37
     paralle
    0.36
     comentar
    0.36
     McCl
    0.36
    Activations Density 0.022%

    No Known Activations