© 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. 44600
    Prev
    Next
    INDEX
    Explanations

    px after activation

    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
     Polish
    0.48
     Mac
    0.45
     Далее
    0.44
    ␤
    0.44
     Jugend
    0.43
     Поль
    0.43
     Beste
    0.41
     Bezos
    0.41
     PNC
    0.41
     გას
    0.41
    POSITIVE LOGITS
     generaciones
    0.41
    峎
    0.38
    ман
    0.38
    navbarSupported
    0.38
    ህ
    0.37
    енера
    0.37
    ச
    0.37
     remove
    0.36
    ত্তম
    0.36
    attoos
    0.36
    Activations Density 0.001%

    No Known Activations