© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161772
    Prev
    Next
    INDEX
    Explanations

    stat/s

    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_2_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
    ر
    1.47
    ik
    1.14
    ো
    1.14
    im
    1.13
    ad
    1.13
    ен
    1.09
    il
    1.07
    ung
    1.07
    م
    1.02
    و
    1.01
    POSITIVE LOGITS
     agrand
    1.00
    by
    0.96
     aident
    0.96
    ้
    0.93
     aument
    0.89
     appel
    0.89
    ם
    0.88
    ent
    0.85
    x
    0.84
    lf
    0.83
    Activations Density 0.002%

    No Known Activations