© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 154353
    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
    0.58
     for
    0.56
     claims
    0.55
    .
    0.54
     of
    0.51
     at
    0.50
     select
    0.49
     claim
    0.49
     transforms
    0.47
     from
    0.47
    POSITIVE LOGITS
    ا
    1.68
    ா
    1.45
    ا۔
    1.02
    ా
    1.02
    다
    0.90
    า
    0.84
    ಾ
    0.75
    ා
    0.75
     Ա
    0.73
    ა
    0.72
    Activations Density 0.000%

    No Known Activations