© 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. 205773
    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
    ى
    1.18
    ని
    1.17
    _
    1.14
    ж
    1.09
    자
    0.96
    이지만
    0.96
     ROUILLER
    0.95
    ENING
    0.92
    家
    0.92
    ৬
    0.91
    POSITIVE LOGITS
     is
    1.37
    ↵
    1.09
     at
    0.99
    ’
    0.94
    out
    0.90
    case
    0.89
    i
    0.87
    ake
    0.86
    ight
    0.84
     indexing
    0.84
    Activations Density 0.000%

    No Known Activations