© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 90840
    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
    y
    0.59
     Shil
    0.48
    i
    0.45
    yh
    0.43
    is
    0.42
     ap
    0.42
    in
    0.42
     ~\
    0.41
    :
    0.41
     cem
    0.41
    POSITIVE LOGITS
    bucket
    0.54
    group
    0.51
     ح
    0.46
    bathtub
    0.46
    bok
    0.44
     الح
    0.44
    engelsk
    0.44
    dalam
    0.43
    má
    0.43
    jong
    0.42
    Activations Density 0.000%

    No Known Activations