© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 50971
    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_10_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
     validations
    0.55
    λογ
    0.55
    ف
    0.51
     Hertz
    0.51
     costing
    0.50
    Jaeger
    0.50
    を指定
    0.49
    সে
    0.49
     Sih
    0.48
    をお
    0.47
    POSITIVE LOGITS
    n
    0.60
    st
    0.58
    ino
    0.54
    rust
    0.54
    s
    0.53
    r
    0.52
    nance
    0.51
    ld
    0.50
    ata
    0.50
    sp
    0.50
    Activations Density 0.000%

    No Known Activations