© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79180
    Prev
    Next
    INDEX
    Explanations

    objectives and conditions

    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_0_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
    는
    1.84
    其他
    1.51
    是
    1.40
    נ
    1.34
    مس
    1.25
    り
    1.23
    は
    1.23
    д
    1.20
    し
    1.19
     своє
    1.17
    POSITIVE LOGITS
     for
    2.03
    at
    1.76
    n
    1.68
    (
    1.62
    el
    1.60
    ik
    1.52
    m
    1.51
    ir
    1.48
    ach
    1.48
    ’
    1.44
    Activations Density 0.000%

    No Known Activations