© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 133405
    Prev
    Next
    INDEX
    Explanations

    Shannon's Sampling Theorem, Model, divergence

    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_1_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
    u
    1.42
    ल
    1.42
    to
    1.35
    ל
    1.34
    ک
    1.31
    ש
    1.30
    ار
    1.27
    า
    1.23
    را
    1.23
    र
    1.17
    POSITIVE LOGITS
    ți
    1.00
    ς
    1.00
    し
    0.98
    :
    0.94
    కు
    0.93
    \
    0.92
    ے
    0.88
    za
    0.85
    даг
    0.83
    aming
    0.83
    Activations Density 0.000%

    No Known Activations