© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60298
    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_2_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
    em
    1.16
     at
    1.13
    ad
    1.08
    h
    1.05
    ط
    1.05
    ot
    1.03
    ur
    0.97
     malé
    0.97
    y
    0.97
    嘏
    0.96
    POSITIVE LOGITS
    ı
    1.42
    も
    1.18
    ان
    1.17
    ు
    1.09
    া
    1.09
    ா
    1.09
    ה
    1.08
    ۲
    1.03
    ा
    1.02
    ון
    1.01
    Activations Density 0.000%

    No Known Activations