© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110263
    Prev
    Next
    INDEX
    Explanations

    ào/ǎo tones

    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
    ON
    1.11
    og
    1.09
    ،
    1.05
     on
    1.03
    ão
    1.02
     the
    1.01
    1.00
    an
    0.98
    IE
    0.96
     an
    0.96
    POSITIVE LOGITS
    i
    2.13
    ي
    1.83
    d
    1.65
    د
    1.63
    י
    1.31
    in
    1.21
    ма
    1.19
    মেয়ে
    1.14
    dh
    1.12
    ി
    1.10
    Activations Density 0.001%

    No Known Activations