© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62725
    Prev
    Next
    INDEX
    Explanations

    months or hours for duration

    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_11_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
    خ
    0.26
    s
    0.25
    ification
    0.24
    فل
    0.23
    ﺷ
    0.23
    سر
    0.23
    \
    0.23
    夸
    0.23
    جه
    0.22
    规模
    0.22
    POSITIVE LOGITS
     жовт
    0.25
     жовтня
    0.25
     pembahasan
    0.25
     подклю
    0.24
    vertrag
    0.23
     Context
    0.22
     Kontext
    0.22
     سمجھ
    0.22
     bekommt
    0.22
     брен
    0.21
    Activations Density 0.007%

    No Known Activations