© 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
    2. Gemma-3-27B-IT
    3. 50-GEMMASCOPE-2-TRANSCODER-262K
    4. 33869
    Prev
    Next
    INDEX
    Explanations

    composer or work

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    클
    0.53
    ક
    0.45
     kie
    0.42
    cl
    0.41
    conc
    0.41
    quiz
    0.41
    Qi
    0.41
    क
    0.41
    CL
    0.40
    OLI
    0.40
    POSITIVE LOGITS
     Bingham
    0.39
     Sultan
    0.39
    跃
    0.38
     Powder
    0.38
    awy
    0.38
    党员
    0.38
     TCU
    0.38
    Ꮹ
    0.38
     sultan
    0.37
    ्यूर
    0.37
    Activations Density 0.003%

    No Known Activations