© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174016
    Prev
    Next
    INDEX
    Explanations

    Lord Shiva

    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_20_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
     উচ্ছ
    0.52
    ⅛
    0.52
    ⅜
    0.50
    theit
    0.48
     hyster
    0.47
    UNDE
    0.47
     Weird
    0.47
     prairie
    0.45
     dimensioni
    0.45
    ⟤
    0.45
    POSITIVE LOGITS
    浓
    0.47
    Table
    0.44
    obu
    0.42
    abstraction
    0.42
    with
    0.41
    <0xB4>
    0.41
     shavings
    0.40
     table
    0.40
     tables
    0.40
     कब्
    0.40
    Activations Density 0.000%

    No Known Activations