© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258466
    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_22_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
     hábito
    0.52
     históricos
    0.46
     নিদর্শন
    0.46
    arquivo
    0.46
    geoLocation
    0.46
     drugih
    0.46
    駒
    0.46
     ró
    0.46
     photography
    0.45
     fotograf
    0.45
    POSITIVE LOGITS
    andled
    0.46
     Paise
    0.45
    睚
    0.44
     Redox
    0.43
    ennessee
    0.43
    喈
    0.42
    initely
    0.42
     paise
    0.41
    蛩
    0.41
    sung
    0.41
    Activations Density 0.000%

    No Known Activations