© 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. 108735
    Prev
    Next
    INDEX
    Explanations

    Japanese word segmentation

    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
    ми
    1.22
    ຜະລິດຕະພັນ
    1.21
    (
    1.20
    </h2>
    1.19
     של
    1.18
     denounced
    1.18
    나
    1.18
    یم
    1.15
    {
    1.12
    нда
    1.11
    POSITIVE LOGITS
    1.60
    ed
    1.33
    f
    1.30
    I
    1.20
    time
    1.18
    o
    1.16
    d
    1.15
    line
    1.14
    。
    1.12
    ।"
    1.11
    Activations Density 0.000%

    No Known Activations