© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107115
    Prev
    Next
    INDEX
    Explanations

    friendship and fruit salad

    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_2_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    あ
    1.11
     calent
    0.99
     it
    0.98
    お
    0.95
    c
    0.95
    د
    0.95
    ма
    0.93
    ിയ
    0.93
    ેર
    0.92
    し
    0.92
    POSITIVE LOGITS
    는
    1.02
    is
    0.93
    もの
    0.91
    是
    0.87
    ни
    0.82
    ının
    0.81
    chaft
    0.80
    for
    0.80
    -
    0.80
    ०
    0.79
    Activations Density 0.004%

    No Known Activations