© 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. 35047
    Prev
    Next
    INDEX
    Explanations

    html lang declaration

    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
    gevity
    0.47
    ciphertext
    0.47
    كُمْ
    0.47
     '$
    0.47
    溱
    0.46
    before
    0.45
    Laundry
    0.45
    ᑐ
    0.45
    おり
    0.45
    궜
    0.45
    POSITIVE LOGITS
     podamos
    0.52
    वीण
    0.51
     mald
    0.49
    িলাম
    0.49
     we
    0.47
     হইতেছিল
    0.47
    adeus
    0.46
     braz
    0.46
    we
    0.46
     hare
    0.46
    Activations Density 0.001%

    No Known Activations