© 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. 141998
    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
    ,
    1.54
    ó
    1.52
    .
    1.42
    tion
    1.38
    G
    1.37
    tte
    1.35
    ()
    1.34
    ä
    1.30
    r
    1.29
    rence
    1.28
    POSITIVE LOGITS
    ка
    1.52
    ۰
    1.48
    ס
    1.38
    在
    1.33
    да
    1.27
    த
    1.25
    <0x80>
    1.17
    ０
    1.16
    مانی
    1.13
    𝟎
    1.13
    Activations Density 0.000%

    No Known Activations