© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 261703
    Prev
    Next
    INDEX
    Explanations

    invested at

    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_22_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
    ётся
    0.21
    莗
    0.19
    队的
    0.19
     צריך
    0.19
    idding
    0.18
    readFile
    0.17
    atu
    0.17
    격을
    0.17
    贲
    0.17
    茼
    0.17
    POSITIVE LOGITS
     doomed
    0.21
    Ѕ
    0.20
    集中
    0.20
     monochrome
    0.20
    Political
    0.20
    Secondo
    0.19
    到
    0.19
     прогнозы
    0.18
     politically
    0.18
     полити
    0.18
    Activations Density 0.001%

    No Known Activations