© 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. 61844
    Prev
    Next
    INDEX
    Explanations

    fabric of society

    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
    of
    1.52
    3
    1.34
    jaman
    1.13
    and
    1.12
    were
    1.08
    もう
    1.04
     количества
    1.04
    々に
    1.03
     ﺍ
    1.01
    ても
    1.00
    POSITIVE LOGITS
    ↵
    2.02
     be
    1.70
    在
    1.55
    U
    1.53
    م
    1.47
     in
    1.45
     في
    1.39
    도
    1.38
    ও
    1.35
    리
    1.34
    Activations Density 0.002%

    No Known Activations