© 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. 42767
    Prev
    Next
    INDEX
    Explanations

    past origins or conditions

    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
    睍
    0.38
     postérieure
    0.37
    粧
    0.34
    聝
    0.33
     vouloir
    0.32
    チル
    0.32
    讀
    0.32
    リティ
    0.31
    ἂ
    0.31
    รัฐ
    0.31
    POSITIVE LOGITS
     academy
    0.34
     прошлом
    0.33
    LoopBlend
    0.33
     academies
    0.32
     высокую
    0.31
     origen
    0.31
     ориги
    0.31
    と思っていた
    0.31
    úncia
    0.31
     pasado
    0.30
    Activations Density 0.022%

    No Known Activations