© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 3669
    Prev
    Next
    INDEX
    Explanations

    print() function calls

    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
     sall
    0.37
     Sall
    0.33
     Там
    0.33
     बाधित
    0.33
     Spacer
    0.31
    解放
    0.31
     '+
    0.30
     آباد
    0.30
    -'].
    0.30
     Salisbury
    0.29
    POSITIVE LOGITS
     out
    0.47
     type
    0.35
     repre
    0.35
     из
    0.34
    代表
    0.32
     representación
    0.31
     represented
    0.31
     eponymous
    0.31
     representative
    0.30
     représenter
    0.30
    Activations Density 0.030%

    No Known Activations