© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 87873
    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_60_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
    yte
    0.49
    y
    0.41
    znac
    0.40
    yas
    0.40
     sifatida
    0.40
    economic
    0.40
    id
    0.40
     матери
    0.39
    quin
    0.38
    cas
    0.38
    POSITIVE LOGITS
     direttore
    0.41
     DMG
    0.40
    ඓ
    0.40
    爌
    0.40
     minimizes
    0.39
     vértice
    0.39
    熹
    0.38
     visionary
    0.38
     vrchol
    0.37
     CARL
    0.37
    Activations Density 0.000%

    No Known Activations