© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84496
    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_0_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
    1
    1.39
    4
    1.28
    6
    1.27
    igh
    1.25
    ו
    1.22
    ER
    1.19
     to
    1.17
    ün
    1.16
    ного
    1.13
    3
    1.13
    POSITIVE LOGITS
     as
    1.51
    できる
    1.51
    h
    1.37
    こと
    1.31
    ت
    1.31
    ⸨
    1.31
    ק
    1.26
     przyję
    1.24
     왔
    1.23
     갔
    1.22
    Activations Density 0.000%

    No Known Activations