© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 236783
    Prev
    Next
    INDEX
    Explanations

    "ok" followed by "{" or "ret" followed by ":"

    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_25_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
    ಲಾಗಿದೆ
    0.44
    updateOne
    0.42
     ভাষ
    0.39
     வெள்ள
    0.38
     unfolded
    0.38
    iencia
    0.38
     trouva
    0.38
    琲
    0.38
     exposição
    0.37
     Worlds
    0.37
    POSITIVE LOGITS
    되며
    0.38
    *(
    0.37
     WY
    0.36
     OS
    0.35
    ԁ
    0.34
    baarheid
    0.34
     барои
    0.33
    '*
    0.32
     머
    0.32
    Ԁ
    0.32
    Activations Density 0.000%

    No Known Activations