© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 156886
    Prev
    Next
    INDEX
    Explanations

    German words starting with gef

    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
    지만
    1.38
    ড
    1.09
    나
    1.09
    ंना
    1.06
    いる
    1.02
    iť
    1.00
    いた
    0.96
    겠습니다
    0.95
    ে
    0.93
    나가
    0.93
    POSITIVE LOGITS
    ли
    1.25
    تها
    1.07
     i
    1.06
    th
    1.05
    O
    1.05
    $.
    1.03
     ut
    1.03
     c
    0.99
    с
    0.99
    cut
    0.97
    Activations Density 0.000%

    No Known Activations