© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42461
    Prev
    Next
    INDEX
    Explanations

    file extensions .py .rs

    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
    edRight
    0.39
    𝐑
    0.39
    এর
    0.37
    𝚁
    0.37
     ninguno
    0.36
    Wrist
    0.36
     derecha
    0.35
     kép
    0.35
    DIC
    0.35
     bunting
    0.35
    POSITIVE LOGITS
    褻
    0.40
     missions
    0.40
    inqui
    0.38
    鹊
    0.37
    亵
    0.37
    missions
    0.37
    另一种
    0.37
    妩
    0.37
     sna
    0.36
     inqui
    0.35
    Activations Density 0.002%

    No Known Activations