© 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. 43073
    Prev
    Next
    INDEX
    Explanations

    most people would say/argue

    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
     sensibles
    0.46
     axles
    0.40
     sensitive
    0.39
     PLEASE
    0.39
    ኽ
    0.39
     দূ
    0.38
    PLEASE
    0.38
    ᱦ
    0.37
     damaged
    0.37
     কাতর
    0.37
    POSITIVE LOGITS
     аласыз
    0.40
     definiciones
    0.40
    arska
    0.39
    laš
    0.38
    ?“
    0.38
     değişiklik
    0.37
     uzak
    0.37
     נמצא
    0.37
     Коло
    0.37
     steepest
    0.37
    Activations Density 0.001%

    No Known Activations