© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 23995
    Prev
    Next
    INDEX
    Explanations

    Harry Kane, Harry Styles, Harry Brook

    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_10_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
    hers
    0.76
    ającą
    0.70
    jaro
    0.68
    ug
    0.65
    )
    0.63
    ag
    0.63
    aldehyde
    0.61
    hok
    0.61
    ayama
    0.59
    ä
    0.59
    POSITIVE LOGITS
     dezvolt
    0.88
     вероятно
    0.76
     baix
    0.74
     the
    0.73
     utiliser
    0.73
     exemplo
    0.72
     souten
    0.72
     ajout
    0.71
     trabal
    0.69
    t
    0.69
    Activations Density 0.001%

    No Known Activations