© 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. 7244
    Prev
    Next
    INDEX
    Explanations

    dar, proceed, expl, capt

    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
     supermarket
    0.37
     tuku
    0.34
     wrangler
    0.34
     Erica
    0.33
     ++)
    0.33
    祜
    0.33
     similit
    0.33
     conda
    0.32
     puk
    0.32
    ')}>
    0.32
    POSITIVE LOGITS
    棒
    0.38
    aughter
    0.37
     rejoindre
    0.36
    স্টার
    0.34
    魇
    0.34
    oring
    0.33
     dar
    0.33
    rds
    0.33
     afront
    0.33
     робити
    0.32
    Activations Density 0.070%

    No Known Activations