© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 230571
    Prev
    Next
    INDEX
    Explanations

    movements

    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_6_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
    v
    1.62
    ü
    1.38
    w
    1.33
    im
    1.29
    m
    1.27
    ina
    1.26
    ill
    1.23
    ut
    1.23
    ok
    1.23
    ra
    1.20
    POSITIVE LOGITS
    '
    1.03
    ນາ
    0.92
    ち
    0.91
    dır
    0.90
    Ligações
    0.86
    まち
    0.84
     chromosomal
    0.82
    ཎ
    0.80
    цију
    0.80
    たん
    0.77
    Activations Density 0.001%

    No Known Activations