© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130485
    Prev
    Next
    INDEX
    Explanations

    deadpan delivery

    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_6_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
    xiety
    0.91
     Ги
    0.85
     Они
    0.84
     မှာ
    0.84
    
    0.83
    <0xAB>
    0.81
     욕
    0.81
     Осо
    0.80
    visory
    0.80
    𝙪
    0.79
    POSITIVE LOGITS
     can
    1.25
    י
    1.16
    ק
    1.16
    า
    1.15
    s
    1.05
    ات
    1.02
    ي
    1.01
    א
    1.01
     of
    0.99
    sons
    0.99
    Activations Density 0.000%

    No Known Activations