© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 215056
    Prev
    Next
    INDEX
    Explanations

    in [location]

    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
    Negative Logits
    क्षण
    0.44
    🔟
    0.43
     unmodified
    0.40
     soundtracks
    0.39
     kotlinx
    0.38
    使得
    0.37
     axially
    0.36
     notwithstanding
    0.36
    萦
    0.36
    anément
    0.36
    POSITIVE LOGITS
    pani
    0.38
    hau
    0.36
    obtain
    0.36
    लोग
    0.35
    ライダー
    0.35
    owners
    0.34
     المحاضره
    0.34
    オーナー
    0.34
    udar
    0.33
     [&
    0.33
    Activations Density 0.002%

    No Known Activations