© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 202523
    Prev
    Next
    INDEX
    Explanations

    字數 or ization

    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_12_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
    不
    0.54
    G
    0.51
    ائمة
    0.51
    straction
    0.50
    อัล
    0.50
     G
    0.49
    stätte
    0.49
    流量
    0.48
    L
    0.48
    跑步
    0.48
    POSITIVE LOGITS
     selon
    0.57
    toj
    0.53
    NCR
    0.53
     curled
    0.52
     stirred
    0.52
     nurtured
    0.52
    টার
    0.51
    氅
    0.49
     nourished
    0.49
    </h3>
    0.49
    Activations Density 0.000%

    No Known Activations