© 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. 35315
    Prev
    Next
    INDEX
    Explanations

    narrow, difficult, easy to maneuver

    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
    boats
    0.37
    }}<
    0.37
    भे
    0.36
    มอ
    0.36
     NAACP
    0.36
    
    0.36
    語
    0.35
     manifolds
    0.35
    σταση
    0.35
    Yvette
    0.35
    POSITIVE LOGITS
     சிங்கள
    0.37
     sang
    0.35
    瑠
    0.35
     ско
    0.34
    ordes
    0.34
     rendered
    0.34
    শ্যাল
    0.34
    selen
    0.34
     deprived
    0.34
     జన
    0.33
    Activations Density 0.017%

    No Known Activations