© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82423
    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
    س
    1.69
    N
    1.21
    S
    1.18
     là
    1.17
    ние
    1.16
     但是
    1.15
     on
    1.13
     năng
    1.12
     لكن
    1.09
     birçok
    1.09
    POSITIVE LOGITS
     be
    1.45
    can
    1.34
    in
    1.31
    ر
    1.26
    told
    1.24
    ها
    1.23
    er
    1.19
    मा
    1.19
    ون
    1.19
    ties
    1.16
    Activations Density 0.000%

    No Known Activations