© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 152546
    Prev
    Next
    INDEX
    Explanations

    trust or confidence

    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_23_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
    <
    0.38
    <i>
    0.37
    <!
    0.35
    சரி
    0.35
     عملکرد
    0.33
    var
    0.33
    任務
    0.33
     сы
    0.33
    াতা
    0.31
     empowered
    0.31
    POSITIVE LOGITS
    磯
    0.44
    ylül
    0.40
     قانونی
    0.40
     لوی
    0.40
     luật
    0.39
     Iso
    0.39
    дания
    0.38
     గొప్ప
    0.38
    盧
    0.38
     destacar
    0.38
    Activations Density 0.002%

    No Known Activations