© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 109500
    Prev
    Next
    INDEX
    Explanations

    ROMs, Pogroms, LineageOS

    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
    它
    1.29
    ne
    1.28
     it
    1.24
    يل
    1.02
    ž
    1.01
    い
    1.00
     distribu
    0.97
    0.97
    et
    0.96
    ım
    0.95
    POSITIVE LOGITS
    را
    1.26
    ت
    1.15
    ード
    1.09
    5
    1.06
    ;
    1.01
    ہ
    0.99
    ه
    0.98
    is
    0.97
    تان
    0.96
    тэй
    0.96
    Activations Density 0.001%

    No Known Activations