© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158908
    Prev
    Next
    INDEX
    Explanations

    defines what comes next

    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
    in
    1.53
    s
    1.02
    and
    0.95
    inizi
    0.88
    inį
    0.88
    ла
    0.87
     GTEST
    0.87
    c
    0.85
    kannya
    0.83
    inprogress
    0.82
    POSITIVE LOGITS
    .
    1.34
    ار
    0.94
    ہ
    0.90
    ز
    0.89
    ី
    0.88
    :
    0.86
    م
    0.86
     contraband
    0.85
    ้
    0.84
    ৭
    0.84
    Activations Density 0.003%

    No Known Activations