© 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. 232401
    Prev
    Next
    INDEX
    Explanations

    aspirational

    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
    begin
    0.89
    ٦
    0.89
     וא
    0.85
    ća
    0.84
     प्राधिकरण
    0.84
     voltam
    0.84
     probado
    0.82
     ويمكن
    0.82
     在
    0.81
     वृन्दावन
    0.80
    POSITIVE LOGITS
    0
    1.37
    ש
    1.20
    1
    1.00
    し
    0.94
    st
    0.93
    ся
    0.87
    ш
    0.84
    shire
    0.82
    <0x80>
    0.81
    yn
    0.80
    Activations Density 0.001%

    No Known Activations