© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33430
    Prev
    Next
    INDEX
    Explanations

    Max Tegmark / visual

    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_3_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
    ۴
    0.76
    ৫
    0.75
    ४
    0.72
    ۵
    0.69
     for
    0.64
    ५
    0.63
     tratando
    0.61
    ختی
    0.59
     byen
    0.59
    elo
    0.59
    POSITIVE LOGITS
    t
    1.10
    j
    0.77
    '
    0.73
    l
    0.72
    nd
    0.65
    lara
    0.65
    _
    0.65
    tions
    0.64
    ן
    0.62
     Einsatz
    0.62
    Activations Density 0.009%

    No Known Activations