© 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. 125992
    Prev
    Next
    INDEX
    Explanations

    background independence vs dependence

    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
    .
    0.70
    ุ
    0.70
    ých
    0.69
    är
    0.68
    יר
    0.67
    ę
    0.64
    í
    0.63
    ัง
    0.59
    יה
    0.59
    ?
    0.58
    POSITIVE LOGITS
    a
    1.02
    ၻ
    0.70
     постро
    0.68
    같이
    0.66
     स्थानांतर
    0.64
    find
    0.63
    vertex
    0.63
    ر
    0.63
    사람
    0.61
    ၷ
    0.61
    Activations Density 0.002%

    No Known Activations