© 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. 129766
    Prev
    Next
    INDEX
    Explanations

    next line

    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
    is
    1.10
    ،
    1.05
    ون
    0.96
    ке
    0.87
    ні
    0.85
    isol
    0.85
    <0xB2>
    0.84
    ри
    0.84
    ي
    0.84
    т
    0.84
    POSITIVE LOGITS
    ta
    1.06
    ž
    1.01
    d
    0.95
    ள்ளதாக
    0.94
    c
    0.94
    in
    0.93
     There
    0.89
     Years
    0.89
     With
    0.88
    si
    0.88
    Activations Density 0.001%

    No Known Activations