© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17859
    Prev
    Next
    INDEX
    Explanations

    English numbers and foreign number 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_40_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
    統一
    0.41
     thous
    0.38
    worthy
    0.38
    ³.
    0.38
    mittent
    0.37
     reflective
    0.37
    的值
    0.36
    ranos
    0.36
    ₃
    0.36
    primary
    0.35
    POSITIVE LOGITS
    getInstalled
    0.46
     deux
    0.45
     दो
    0.43
     двумя
    0.43
     Deux
    0.43
     iki
    0.42
    Deux
    0.42
     dua
    0.41
     kaks
    0.40
     Два
    0.40
    Activations Density 0.000%

    No Known Activations