© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 132549
    Prev
    Next
    INDEX
    Explanations

    Returns

    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
    हमी
    0.40
    济
    0.40
    atul
    0.38
     Laval
    0.38
    ferencia
    0.37
    }$&$-
    0.37
    ',"
    0.37
     Twp
    0.36
    ザ
    0.36
     Tah
    0.36
    POSITIVE LOGITS
    triple
    0.44
    Triple
    0.40
     triple
    0.39
     dieci
    0.39
     Anything
    0.38
    Anything
    0.38
    Anyone
    0.37
    گان
    0.36
     ट्रिपल
    0.36
    Anybody
    0.36
    Activations Density 0.002%

    No Known Activations