© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 143026
    Prev
    Next
    INDEX
    Explanations

    Laravel framework

    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_0_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
    \
    1.85
    (
    1.60
     of
    1.48
    كل
    1.46
     ي
    1.45
    قة
    1.37
    తో
    1.34
    كه
    1.31
    كم
    1.27
    كي
    1.25
    POSITIVE LOGITS
    m
    1.98
    ir
    1.98
    ید
    1.98
    n
    1.94
    in
    1.85
    et
    1.70
    ed
    1.70
    ান
    1.66
    িন
    1.63
    f
    1.62
    Activations Density 0.001%

    No Known Activations