© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 174752
    Prev
    Next
    INDEX
    Explanations

    find that

    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_24_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
     கொள்ளலாம்
    0.40
    ާތ
    0.40
     ideology
    0.40
     компью
    0.40
     기반
    0.39
     компьютер
    0.39
     เพื่อ
    0.39
     Croatian
    0.39
    捃
    0.39
     sideWeight
    0.38
    POSITIVE LOGITS
    oths
    0.48
    enen
    0.46
    쨋
    0.45
    lil
    0.45
    dies
    0.45
    shima
    0.44
    enol
    0.44
    ins
    0.44
    item
    0.44
     ternyata
    0.44
    Activations Density 0.001%

    No Known Activations