© 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. 106885
    Prev
    Next
    INDEX
    Explanations

    divergence of interests or paths

    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
    Negative Logits
    ב
    1.14
    ة
    1.01
    한
    0.97
    ס
    0.86
    д
    0.84
    м
    0.84
    ü
    0.82
    к
    0.82
    个
    0.82
    ب
    0.80
    POSITIVE LOGITS
    f
    1.01
    fice
    0.73
    ig
    0.65
    ika
    0.64
    々は
    0.63
    tti
    0.63
    vot
    0.63
    adera
    0.62
    azioni
    0.61
    nego
    0.60
    Activations Density 0.000%

    No Known Activations