© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 209129
    Prev
    Next
    INDEX
    Explanations

    thread pool

    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
    但他
    0.41
    IsMethod
    0.41
     লৌ
    0.40
    㐰
    0.40
    JUD
    0.39
    <0xB5>
    0.39
    ινε
    0.39
    เขา
    0.38
    ﾋ
    0.38
     Bela
    0.38
    POSITIVE LOGITS
     ఛ
    0.47
     ස්
    0.46
     acres
    0.46
     चलती
    0.45
    каў
    0.43
     afectar
    0.43
     précis
    0.43
    Charset
    0.42
     validType
    0.42
    ্যের
    0.42
    Activations Density 0.000%

    No Known Activations