© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 220152
    Prev
    Next
    INDEX
    Explanations

    PowerPoint, docx, slide, shapes

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ιασ
    0.38
    サリー
    0.36
     Schenectady
    0.36
     ઉજ
    0.36
    
    0.35
     Cuth
    0.34
     应
    0.34
    simx
    0.34
    Boa
    0.34
     Flanagan
    0.34
    POSITIVE LOGITS
    '$\
    0.45
     margins
    0.42
    margins
    0.40
     secretary
    0.40
     "=
    0.40
     olymp
    0.39
     margen
    0.39
     Olymp
    0.39
     Cid
    0.38
     XPS
    0.37
    Activations Density 0.004%

    No Known Activations