© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 129731
    Prev
    Next
    INDEX
    Explanations

    depenent

    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
    지
    1.20
    se
    0.85
    ;
    0.83
    це
    0.81
    ja
    0.78
    ти
    0.77
    _
    0.77
    )
    0.75
    其他
    0.75
    тов
    0.72
    POSITIVE LOGITS
    m
    1.34
    ا
    1.34
    s
    1.23
    rf
    1.11
    y
    1.05
    ri
    1.03
    ik
    1.02
    to
    1.00
    다
    1.00
    b
    0.98
    Activations Density 0.000%

    No Known Activations