© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 134567
    Prev
    Next
    INDEX
    Explanations

    snapped

    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
    。
    1.02
    '
    0.93
    ".
    0.87
     flaming
    0.76
    ized
    0.75
    <
    0.73
     Eiffel
    0.72
    ).
    0.71
     använd
    0.71
     simplic
    0.71
    POSITIVE LOGITS
    o
    1.70
    ص
    1.59
    و
    1.46
    ו
    1.42
    ق
    1.41
    ስ
    1.40
    q
    1.39
    s
    1.31
    ج
    1.29
    ul
    1.27
    Activations Density 0.001%

    No Known Activations