© 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. 177470
    Prev
    Next
    INDEX
    Explanations

    Don

    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
     Anne
    0.42
     Hester
    0.40
     vale
    0.39
    녕
    0.39
     Shi
    0.39
     Bak
    0.38
     Ut
    0.38
     anne
    0.38
    Anne
    0.38
     Saves
    0.37
    POSITIVE LOGITS
     इज
    0.41
    ｦ
    0.40
    gitian
    0.39
     السود
    0.38
    σει
    0.38
     изо
    0.38
     glTranslatef
    0.38
    Flight
    0.38
    nucleon
    0.38
    狨
    0.37
    Activations Density 0.000%

    No Known Activations