© 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. 58673
    Prev
    Next
    INDEX
    Explanations

    japanese particles and words

    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
    在
    0.97
     tué
    0.97
     provoqu
    0.94
    .
    0.94
     quintessential
    0.93
     られ
    0.92
    아요
    0.91
     veng
    0.91
    It
    0.89
     I
    0.89
    POSITIVE LOGITS
    as
    1.51
    an
    1.36
    on
    1.35
    ان
    1.34
    ता
    1.34
    ة
    1.29
     are
    1.23
    ic
    1.16
    ло
    1.15
    يا
    1.13
    Activations Density 0.012%

    No Known Activations