© 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. 216427
    Prev
    Next
    INDEX
    Explanations

    Guillermo

    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
    薜
    0.44
     defied
    0.43
     defy
    0.42
    hams
    0.40
    hrt
    0.39
    滄
    0.39
     Bache
    0.38
    వాన్ని
    0.38
    πους
    0.38
    πος
    0.38
    POSITIVE LOGITS
    Ya
    0.49
    Yas
    0.45
     Ya
    0.43
    Jen
    0.43
    Noir
    0.41
    YA
    0.41
    朵
    0.40
     Noir
    0.40
    Gov
    0.40
    ekten
    0.40
    Activations Density 0.000%

    No Known Activations