© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89799
    Prev
    Next
    INDEX
    Explanations

    nature, figure, obscure

    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
    ed
    0.89
    t
    0.75
    y
    0.62
    <0x8C>
    0.62
    er
    0.62
    做了
    0.60
    ੰ
    0.59
    vscode
    0.57
    tj
    0.57
    n
    0.57
    POSITIVE LOGITS
    、
    0.66
    ка
    0.65
    ক
    0.65
     của
    0.64
    breeding
    0.64
     electors
    0.63
     are
    0.60
     в
    0.60
     hóa
    0.59
     vya
    0.59
    Activations Density 0.000%

    No Known Activations