© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2506
    Prev
    Next
    INDEX
    Explanations

    Sup or Supreme variants

    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_39_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
     అ
    0.37
     편
    0.37
     interventi
    0.36
    
    0.36
     domes
    0.36
     Stokes
    0.35
     stort
    0.35
    绚
    0.35
     depre
    0.34
    Blake
    0.34
    POSITIVE LOGITS
     overlay
    0.40
    ckel
    0.39
    Paula
    0.39
    amentul
    0.38
     लॉन्च
    0.37
    पाट
    0.37
     लुक
    0.37
     launch
    0.37
     Paula
    0.37
     fats
    0.37
    Activations Density 0.029%

    No Known Activations