© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 203786
    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_46_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
    `),
    0.37
    ulia
    0.36
    pr
    0.35
     SDLK
    0.34
    करें
    0.33
    leftarrow
    0.33
    ขาว
    0.33
    antoin
    0.33
     descart
    0.32
     Darling
    0.32
    POSITIVE LOGITS
    Benzyloxy
    0.43
    Natural
    0.41
    栘
    0.41
     Introducing
    0.40
    Marks
    0.39
    止
    0.39
    Introducing
    0.39
    INTRO
    0.39
     tunneling
    0.39
    SOURCES
    0.39
    Activations Density 0.000%

    No Known Activations