© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 154575
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_23_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
     quinto
    0.54
     really
    0.50
     fonctionne
    0.49
    巖
    0.47
     considère
    0.47
     aceler
    0.46
     seterusnya
    0.46
     almeno
    0.45
     cuantos
    0.45
     Brésil
    0.45
    POSITIVE LOGITS
    ide
    0.45
    ista
    0.44
    marginal
    0.42
    জেলা
    0.42
    ostasis
    0.42
    /
    0.42
    \&
    0.41
    loaf
    0.40
    isti
    0.40
    profile
    0.39
    Activations Density 0.000%

    No Known Activations