© 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. 261882
    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
    )/
    0.50
    )।
    0.47
     spun
    0.46
     cellular
    0.44
    EY
    0.43
    aris
    0.42
    !)
    0.42
     vivido
    0.41
    TIMESTAMP
    0.41
    ,/
    0.41
    POSITIVE LOGITS
    开始
    0.52
    珲
    0.51
     appartement
    0.49
    وحة
    0.49
     mismas
    0.47
    u
    0.47
    िक
    0.47
     cadena
    0.47
    Marca
    0.46
     murió
    0.46
    Activations Density 0.000%

    No Known Activations