© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 83099
    Prev
    Next
    INDEX
    Explanations

    the answer is complex

    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_29_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
     {!
    0.39
    {\"
    0.38
    )"))
    0.37
     Bouchard
    0.37
    ([...
    0.36
     much
    0.36
    धि
    0.36
    적으로
    0.36
     zahval
    0.36
     affine
    0.36
    POSITIVE LOGITS
    ላሉ
    0.39
     видно
    0.36
     дополнительных
    0.34
    もし
    0.34
    cklen
    0.33
     sò
    0.33
    闪
    0.33
     granularity
    0.32
     جدول
    0.32
     bà
    0.32
    Activations Density 0.011%

    No Known Activations