© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 209587
    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_10_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
    ώ
    0.49
    ২
    0.48
    dır
    0.47
    产生
    0.46
    ır
    0.45
    ıma
    0.45
     تک
    0.44
    ر
    0.44
     massif
    0.43
     বাড়
    0.43
    POSITIVE LOGITS
    𝙇
    0.66
     workday
    0.47
    DON
    0.47
    一句
    0.47
     गिरफ्त
    0.46
    AS
    0.46
     buddha
    0.45
    gill
    0.45
    ClNO
    0.45
    LOSS
    0.45
    Activations Density 0.000%

    No Known Activations