© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 207093
    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_56_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
     Heid
    0.35
     حركة
    0.34
     heller
    0.34
    ಲೆ
    0.33
     محم
    0.33
    堺
    0.33
     abort
    0.32
     onError
    0.32
     Albrecht
    0.32
     alerg
    0.32
    POSITIVE LOGITS
    s
    0.71
    ی
    0.63
    sning
    0.47
    ের
    0.47
    sø
    0.46
    いる
    0.46
    shed
    0.44
    ి
    0.43
    到的
    0.42
    sent
    0.42
    Activations Density 0.000%

    No Known Activations