© 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. 107439
    Prev
    Next
    INDEX
    Explanations

    Japanese question marker ka

    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
    ne
    1.18
     is
    1.16
     are
    1.16
    ä
    1.08
    filtration
    1.02
    いた
    1.01
    apak
    0.98
    tained
    0.98
     ਅਤੇ
    0.98
    ामध्ये
    0.95
    POSITIVE LOGITS
    و
    1.70
    il
    1.43
    ین
    1.42
    م
    1.36
    in
    1.32
    ו
    1.31
    ل
    1.20
     comprob
    1.16
     colet
    1.14
    أ
    1.13
    Activations Density 0.000%

    No Known Activations