© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 238125
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_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
    andum
    0.40
    随时
    0.39
    隨
    0.38
     Neend
    0.38
    sand
    0.37
     Temperature
    0.36
    isk
    0.35
     Makeup
    0.35
     Bundle
    0.35
     পারা
    0.35
    POSITIVE LOGITS
     motivating
    0.42
     exist
    0.40
    👏👏👏👏
    0.40
     captivity
    0.40
     adulthood
    0.39
     существуют
    0.39
     abolition
    0.38
     esist
    0.38
     exists
    0.38
     selective
    0.38
    Activations Density 0.000%

    No Known Activations