© 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-3-4B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-16K
    7. 993
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_12_width_16k_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
     kids
    0.57
     adolescents
    0.53
     ambulances
    0.53
     Hendrix
    0.53
    <unused2221>
    0.53
     opponents
    0.53
     Sriniv
    0.52
     toddlers
    0.52
     broadcasters
    0.52
     kid
    0.52
    POSITIVE LOGITS
     ninguna
    0.54
    exclusion
    0.50
     травня
    0.48
     $("#"
    0.48
     службу
    0.47
    특별
    0.46
     différentes
    0.45
     Excluding
    0.45
    excluded
    0.45
     tránh
    0.45
    Activations Density 0.023%

    No Known Activations