© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158427
    Prev
    Next
    INDEX
    Explanations

    Czech and Slovak place names

    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_2_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
    1.41
    ing
    1.20
    ۔
    1.13
     panicked
    1.03
    in
    1.00
    ።
    1.00
     idealized
    0.96
     beamed
    0.95
    是
    0.92
     fared
    0.92
    POSITIVE LOGITS
    на
    1.61
     for
    1.36
     as
    1.36
    for
    1.10
    のマ
    1.04
    та
    1.01
    ू
    1.01
    ει
    1.00
    ↵↵
    0.99
    таж
    0.95
    Activations Density 0.000%

    No Known Activations