© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 193655
    Prev
    Next
    INDEX
    Explanations

    some resources:

    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_9_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
     nascita
    0.91
    čkog
    0.90
     dispositivi
    0.87
     vérité
    0.84
     costituito
    0.84
     condizione
    0.81
    치
    0.81
     funzione
    0.81
     comunità
    0.81
     tratamento
    0.80
    POSITIVE LOGITS
    s
    0.99
    S
    0.92
     in
    0.91
    ט
    0.89
     S
    0.87
    si
    0.84
    ik
    0.82
     a
    0.79
     =
    0.79
    il
    0.77
    Activations Density 0.052%

    No Known Activations