© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82064
    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_0_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
    '
    0.59
     আইনের
    0.54
    atoires
    0.53
    im
    0.51
     épouse
    0.50
    core
    0.47
    époque
    0.47
    ut
    0.46
    resource
    0.46
    created
    0.46
    POSITIVE LOGITS
     heart
    0.49
     ಹೃ
    0.45
     chunk
    0.45
     heartbreaking
    0.43
     हृदय
    0.43
     心
    0.43
     hlad
    0.43
     compliment
    0.43
     rhs
    0.42
     ಹೃದಯ
    0.42
    Activations Density 0.000%

    No Known Activations