© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 223034
    Prev
    Next
    INDEX
    Explanations

    minor followed by a noun

    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_10_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
    u
    0.23
    İ
    0.19
    জ
    0.19
    IC
    0.19
    ع
    0.18
     zašt
    0.18
    ه
    0.18
    ו
    0.17
    II
    0.17
    IS
    0.17
    POSITIVE LOGITS
     дзе
    0.18
     modellen
    0.18
    ្នែក
    0.18
     actuated
    0.18
    ॉक्स
    0.18
     deformation
    0.17
     изображения
    0.17
     अनुसंधान
    0.17
     हैव
    0.17
     Janeiro
    0.17
    Activations Density 0.008%

    No Known Activations