© 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. 144254
    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
    wyczaj
    0.53
    calories
    0.52
    name
    0.51
    leyeceğiz
    0.51
    beauty
    0.51
    kę
    0.50
    catalog
    0.50
    k
    0.49
    К
    0.49
    bigg
    0.48
    POSITIVE LOGITS
     Warrior
    0.48
     Strasbourg
    0.46
     an
    0.45
     warrior
    0.45
     demonic
    0.45
     German
    0.43
    емых
    0.42
     Marxist
    0.42
     Baseball
    0.42
     cinch
    0.41
    Activations Density 0.000%

    No Known Activations