© 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. 109906
    Prev
    Next
    INDEX
    Explanations

    H followed by 'o' or 'Hø'

    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
     as
    1.40
    س
    1.36
    с
    1.35
    ä
    1.35
    ט
    1.30
    as
    1.28
     It
    1.27
    ون
    1.25
    िंग
    1.22
    م
    1.22
    POSITIVE LOGITS
    Р
    1.16
    H
    1.09
    Z
    0.99
    U
    0.99
    c
    0.98
    ει
    0.90
    のために
    0.89
     dụng
    0.88
    kje
    0.88
     orice
    0.87
    Activations Density 0.000%

    No Known Activations