© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 49733
    Prev
    Next
    INDEX
    Explanations

    for [followed by noun/purpose]

    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_31_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
     کاربران
    0.35
     manut
    0.31
    ใคร
    0.31
     пользователей
    0.30
    ポーター
    0.30
     users
    0.30
    oving
    0.30
    媢
    0.30
    ючи
    0.29
     والوں
    0.29
    POSITIVE LOGITS
     തന്റെ
    0.35
     своём
    0.33
     svojih
    0.33
     shellcheck
    0.32
     Hepburn
    0.31
     ettiği
    0.31
    덟
    0.31
     своих
    0.31
     Ihrer
    0.31
     suas
    0.31
    Activations Density 0.006%

    No Known Activations