© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89235
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers

    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_23_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
    budget
    0.35
    清楚
    0.32
    უალ
    0.31
    mode
    0.30
    string
    0.30
    쌍
    0.30
    LEVEL
    0.30
     दोगु
    0.29
    Decoding
    0.29
    py
    0.29
    POSITIVE LOGITS
     بالن
    0.33
     registra
    0.33
     registration
    0.30
    登记
    0.30
    邝
    0.30
     monolithic
    0.30
     đăng
    0.30
     теркә
    0.30
     kona
    0.30
     exhib
    0.29
    Activations Density 0.002%

    No Known Activations