© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 142793
    Prev
    Next
    INDEX
    Explanations

    roles or people

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     ஆத
    0.41
     officials
    0.40
     built
    0.39
     […]
    0.38
     established
    0.38
    ……”
    0.38
     Established
    0.38
    __["
    0.37
     étab
    0.37
    充
    0.37
    POSITIVE LOGITS
    侄
    0.44
    姪
    0.44
     ஒன்றியம்
    0.43
     division
    0.42
    isierten
    0.40
    ISER
    0.38
    पूर
    0.38
    mujer
    0.38
    Division
    0.38
     радиа
    0.37
    Activations Density 0.001%

    No Known Activations