© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12257
    Prev
    Next
    INDEX
    Explanations

    browser related programming

    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
    psons
    0.41
    껴
    0.41
    ⓶
    0.40
     oscill
    0.38
     magni
    0.38
     imputation
    0.38
     ഓഫ
    0.38
     Beer
    0.37
     бк
    0.36
     Cabin
    0.36
    POSITIVE LOGITS
     dehydrated
    0.39
    cex
    0.39
    idez
    0.39
    oule
    0.38
    
    0.36
     wiped
    0.35
    aS
    0.35
    䥑
    0.35
     neun
    0.35
    endela
    0.34
    Activations Density 0.006%

    No Known Activations