© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130359
    Prev
    Next
    INDEX
    Explanations

    detecting

    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_1_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
    '
    1.34
    도
    1.31
    在
    1.28
    高速
    1.21
    它
    1.10
    一定的
    1.06
    )
    1.05
    在本
    1.04
    :
    1.02
    ↵
    0.99
    POSITIVE LOGITS
    ні
    1.73
    s
    1.67
    t
    1.59
    m
    1.53
    ן
    1.48
    the
    1.45
    st
    1.38
    il
    1.35
    v
    1.35
    mi
    1.29
    Activations Density 0.007%

    No Known Activations