© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34319
    Prev
    Next
    INDEX
    Explanations

    Awesome Oscillator, Awesome Mix, NullException

    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_3_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
    お知らせ
    0.67
    猢
    0.64
    猁
    0.62
    alions
    0.61
    MUX
    0.59
    ^{[\
    0.59
    NEUTRON
    0.59
    fetch
    0.58
    ኺ
    0.57
    examples
    0.56
    POSITIVE LOGITS
    ）
    0.86
    О
    0.78
    เป็น
    0.74
    ne
    0.74
     awesome
    0.73
    ט
    0.72
    )
    0.71
    س
    0.71
    ）,
    0.65
    1
    0.63
    Activations Density 0.001%

    No Known Activations