© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 232264
    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_6_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
     to
    0.95
    یس
    0.81
    はい
    0.79
    ğ
    0.79
    ids
    0.76
     was
    0.75
    ון
    0.74
    ,
    0.74
    ור
    0.73
    บ
    0.73
    POSITIVE LOGITS
    và
    0.90
    n
    0.89
    da
    0.81
    denoted
    0.77
    h
    0.77
     thei
    0.77
     Tattha
    0.76
     vatt
    0.70
     Geç
    0.69
     सदी
    0.69
    Activations Density 0.000%

    No Known Activations