© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 62128
    Prev
    Next
    INDEX
    Explanations

    execution context

    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
    戞
    0.89
    ঃ
    0.84
    op
    0.84
    are
    0.84
     indicar
    0.84
     shoving
    0.82
    $
    0.80
    have
    0.77
     exertions
    0.77
     hizo
    0.76
    POSITIVE LOGITS
    ي
    1.74
    ش
    1.70
    م
    1.63
    ط
    1.53
    ح
    1.48
    أ
    1.44
    ق
    1.42
    но
    1.38
    не
    1.37
    ع
    1.34
    Activations Density 0.005%

    No Known Activations