© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174077
    Prev
    Next
    INDEX
    Explanations

    for the most part

    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_20_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
    簋
    0.50
     davon
    0.45
     olie
    0.44
    apaccay
    0.43
    లలో
    0.43
    <unused415>
    0.43
     determinants
    0.42
    铢
    0.42
     кораб
    0.42
    嘤
    0.42
    POSITIVE LOGITS
    /
    0.47
    uti
    0.40
    webs
    0.39
     realistic
    0.39
    uwe
    0.38
    rw
    0.38
    wek
    0.38
    identify
    0.38
    íst
    0.38
    unt
    0.37
    Activations Density 0.000%

    No Known Activations