© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 205833
    Prev
    Next
    INDEX
    Explanations

    Dirichlet multinomial distribution

    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_37_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
    解锁
    0.40
     construye
    0.39
     Tuna
    0.39
     CDB
    0.39
     தொலைக்கா
    0.38
     Bernard
    0.38
    褴
    0.38
     品
    0.38
     Helic
    0.38
    环境中
    0.38
    POSITIVE LOGITS
     കൂട
    0.51
    amsmath
    0.42
     Dirichlet
    0.41
     Mult
    0.40
     mult
    0.39
     multin
    0.39
    dup
    0.38
    zał
    0.38
     multim
    0.37
    Mult
    0.37
    Activations Density 0.000%

    No Known Activations