© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 65779
    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_41_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
     Yahoo
    2.34
    Yahoo
    2.20
     yahoo
    2.00
    yahoo
    1.81
    雅
    1.30
     Yah
    1.30
     야
    1.21
    Yah
    1.20
     YA
    1.19
     yah
    1.14
    POSITIVE LOGITS
     NAS
    0.43
     kip
    0.42
    礬
    0.40
    kip
    0.39
    ㎏
    0.39
     AC
    0.38
    Ren
    0.38
     Kip
    0.38
    䘚
    0.37
     sark
    0.36
    Activations Density 0.011%

    No Known Activations