© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 52025
    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_30_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
    btnInventory
    0.40
    钛
    0.37
    cvt
    0.36
     अल्ट
    0.36
    Race
    0.35
    imitives
    0.35
    懶
    0.35
    converted
    0.34
    ReactNativeHost
    0.34
     récent
    0.34
    POSITIVE LOGITS
    agers
    0.40
     assumptions
    0.39
    issão
    0.39
     Opp
    0.39
     resemblance
    0.38
     attribution
    0.37
    ǎ
    0.37
     Pamp
    0.36
     asociación
    0.35
     Hendrix
    0.35
    Activations Density 0.000%

    No Known Activations