© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83551
    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_0_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
    ari
    1.40
    The
    1.11
    ط
    1.11
     Territory
    1.07
    ල
    1.07
     Engineers
    1.05
    '
    1.05
    ru
    1.03
     Ejecutivo
    1.03
     The
    1.02
    POSITIVE LOGITS
     to
    1.76
     dilapidated
    1.42
     retort
    1.42
     perfused
    1.41
    ו
    1.39
     frayed
    1.38
    なる
    1.38
    ம்
    1.37
    с
    1.36
    س
    1.35
    Activations Density 0.000%

    No Known Activations