© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35135
    Prev
    Next
    INDEX
    Explanations

    LaTeX math environments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
    媺
    0.38
    辭
    0.35
    짊
    0.34
    зом
    0.32
    ريقه
    0.32
     IMHO
    0.32
    testGet
    0.31
     escritório
    0.31
    詣
    0.31
     Rxc
    0.30
    POSITIVE LOGITS
     viol
    0.33
     sion
    0.33
     attachments
    0.32
    თა
    0.32
     Jarrett
    0.32
     anchorage
    0.32
     occupy
    0.32
     mutually
    0.32
    銮
    0.32
     confessed
    0.31
    Activations Density 0.004%

    No Known Activations