© 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. 31559
    Prev
    Next
    INDEX
    Explanations

    CAD, design, and sketching

    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
    রাল
    0.37
    SSL
    0.36
    缦
    0.36
    NT
    0.35
     fingert
    0.34
     GP
    0.34
    XI
    0.33
    悶
    0.33
     amni
    0.33
    Coluna
    0.33
    POSITIVE LOGITS
     CAD
    1.41
     AutoCAD
    1.32
    CAD
    1.27
     sketch
    1.20
     Sketch
    1.20
    Sketch
    1.19
     sketching
    1.19
     drawings
    1.17
     sketches
    1.16
     rendering
    1.12
    Activations Density 0.047%

    No Known Activations