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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44160
    Prev
    Next
    INDEX
    Explanations

    Dragon King, throne, tattoo, writer

    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
    Not in Any Lists

    No Comments

    Negative Logits
     V
    0.73
    n
    0.72
    e
    0.67
    ");
    0.67
     rey
    0.65
    ).
    0.64
     F
    0.64
     G
    0.64
     ter
    0.64
     Pa
    0.64
    POSITIVE LOGITS
    S
    0.72
    ля
    0.68
    вя
    0.68
    limiting
    0.68
    G
    0.68
    lac
    0.67
    polished
    0.66
    л
    0.66
    것
    0.66
    ки
    0.66
    Activations Density 0.011%

    No Known Activations