© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 177334
    Prev
    Next
    INDEX
    Explanations

    find more information

    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
     S
    0.40
    послед
    0.38
     bract
    0.38
    гром
    0.36
    zied
    0.36
    氀
    0.35
    zeugt
    0.35
     mengenal
    0.35
    bapt
    0.35
    ipient
    0.34
    POSITIVE LOGITS
     Entomology
    0.40
    リング
    0.37
    €
    0.36
    Œ
    0.35
    ”
    0.35
    ্রান্ত
    0.33
     حلقه
    0.33
    Aqui
    0.33
    •
    0.33
     wholly
    0.33
    Activations Density 0.000%

    No Known Activations