© 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. 43705
    Prev
    Next
    INDEX
    Explanations

    ball

    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
    0
    0.76
    ,
    0.71
    ہ
    0.61
     hypothes
    0.60
    1
    0.60
    a
    0.59
     увеличи
    0.59
    u
    0.57
    <strong>
    0.55
    }>
    0.55
    POSITIVE LOGITS
    awaiter
    0.72
    лика
    0.68
    yto
    0.67
    то
    0.66
    مان
    0.66
    ليه
    0.66
    با
    0.66
    гам
    0.66
    یت
    0.65
    работка
    0.65
    Activations Density 0.001%

    No Known Activations