© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 141091
    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_46_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
    скім
    0.41
     шам
    0.40
    🧣
    0.40
    ⏜
    0.40
     vín
    0.39
     कण
    0.38
     досто
    0.37
     interoper
    0.36
     Pane
    0.36
    NESDAY
    0.36
    POSITIVE LOGITS
    轩
    0.42
    軒
    0.40
    punch
    0.39
    renched
    0.38
     Finch
    0.38
     зберіга
    0.38
     मिरची
    0.37
     मिल्
    0.37
     кише
    0.36
    愠
    0.36
    Activations Density 0.000%

    No Known Activations