© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 197466
    Prev
    Next
    INDEX
    Explanations

    Make, Berkeley

    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_50_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
    alai
    0.42
    Kor
    0.40
    বাহী
    0.39
    영
    0.39
    inian
    0.39
     Tait
    0.38
    il
    0.38
    પ
    0.37
    enaries
    0.37
    ented
    0.37
    POSITIVE LOGITS
    tumblr
    0.38
    भीर
    0.38
    ]]);
    0.38
     Jed
    0.37
     எடு
    0.37
     Ortega
    0.37
    及ひ
    0.37
     आश्
    0.36
    इंद
    0.36
     rite
    0.36
    Activations Density 0.001%

    No Known Activations