© 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. 53025
    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
    dtd
    0.39
    プ
    0.39
    пиа
    0.38
    浦
    0.37
    得以
    0.37
     प्रो
    0.36
    医
    0.36
    ꯤ
    0.36
     الاجابه
    0.35
     yapılan
    0.35
    POSITIVE LOGITS
    attho
    0.40
    eno
    0.38
    ίνη
    0.37
     অসম্ভব
    0.36
     tomo
    0.36
     perfect
    0.36
    |</
    0.36
     perfetto
    0.36
    anyo
    0.35
     INCIDENTAL
    0.35
    Activations Density 0.000%

    No Known Activations