© 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. 158617
    Prev
    Next
    INDEX
    Explanations

    Anne

    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
    гин
    0.39
    ágina
    0.39
     dég
    0.39
     Ат
    0.39
    γου
    0.38
     zare
    0.37
    deg
    0.37
    拽
    0.36
     deg
    0.35
     (__
    0.35
    POSITIVE LOGITS
    arne
    0.46
    anne
    0.41
    leep
    0.40
     felf
    0.38
    iria
    0.38
    irmi
    0.38
    부를
    0.38
     Braves
    0.37
    ided
    0.37
    Anne
    0.37
    Activations Density 0.000%

    No Known Activations