© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 128872
    Prev
    Next
    INDEX
    Explanations

    Arc de

    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_6_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
    ED
    1.40
    it
    1.29
    at
    1.28
    in
    1.24
     to
    1.16
    ed
    1.15
    ul
    1.09
    ي
    1.09
    ة
    1.08
    i
    1.07
    POSITIVE LOGITS
     dowol
    0.88
     campione
    0.86
     extrêmement
    0.84
     bellissimo
    0.84
     coseno
    0.82
     uczni
    0.82
     horticulture
    0.81
     élargies
    0.81
     biznes
    0.80
     europeo
    0.79
    Activations Density 0.000%

    No Known Activations