© 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. 166685
    Prev
    Next
    INDEX
    Explanations

    I'll + verb

    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
     meaningful
    0.36
     nyní
    0.34
     delayed
    0.33
     oysters
    0.33
    腰
    0.33
     अतिक्रमण
    0.33
     habíamos
    0.33
     позд
    0.32
     proč
    0.32
     Η
    0.32
    POSITIVE LOGITS
    Opt
    0.38
     Selon
    0.35
    Characters
    0.34
    畱
    0.33
     说明
    0.31
    cerpt
    0.31
     exhibit
    0.31
    herence
    0.31
    留在
    0.31
    rieved
    0.31
    Activations Density 0.001%

    No Known Activations