© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37037
    Prev
    Next
    INDEX
    Explanations

    ca

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
     बेटा
    0.38
    大概
    0.38
     zach
    0.36
    寛
    0.36
    izat
    0.35
     sedation
    0.35
    Zach
    0.34
    战
    0.34
    ()<<
    0.33
     habit
    0.33
    POSITIVE LOGITS
     ca
    0.61
     Ca
    0.59
     cir
    0.57
     Et
    0.50
     et
    0.50
    ca
    0.48
     cauliflower
    0.47
     mind
    0.46
    Ca
    0.46
    Et
    0.45
    Activations Density 0.001%

    No Known Activations