© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163147
    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_31_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
    ண்டி
    0.39
     clar
    0.37
    hasil
    0.36
    醫
    0.36
     值
    0.35
    汲
    0.35
    एस्ट
    0.35
     sila
    0.34
     জমির
    0.34
     raíces
    0.34
    POSITIVE LOGITS
     Neon
    0.38
    icidal
    0.37
    ipeline
    0.37
     Dialogue
    0.37
    올
    0.37
     FCC
    0.36
    仍然
    0.35
     Продол
    0.34
     coment
    0.34
     भाषण
    0.34
    Activations Density 0.000%

    No Known Activations