© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 36032
    Prev
    Next
    INDEX
    Explanations

    little followed by descriptors

    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_7_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
     o
    0.42
     le
    0.40
     c
    0.39
     e
    0.39
     op
    0.38
     opal
    0.38
     d
    0.37
     and
    0.37
     f
    0.36
     air
    0.36
    POSITIVE LOGITS
    к
    0.42
    ن
    0.42
    n
    0.36
     Verificar
    0.36
    that
    0.34
    न
    0.33
     Função
    0.33
    un
    0.32
    ла
    0.31
     Méd
    0.31
    Activations Density 0.017%

    No Known Activations