© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38242
    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_57_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
    하시
    0.38
    無く
    0.38
    atable
    0.37
     تعط
    0.36
    淑
    0.36
    ঁচু
    0.35
    ఞ
    0.34
    passwd
    0.34
    攸
    0.34
    Philipp
    0.33
    POSITIVE LOGITS
    od
    0.41
    ő
    0.41
    ียว
    0.40
    वासन
    0.39
     garantia
    0.39
    nées
    0.39
     taal
    0.38
     tet
    0.38
     ти
    0.37
     saute
    0.37
    Activations Density 0.000%

    No Known Activations