© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120524
    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_27_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
    ającym
    0.51
    অনেক
    0.51
    ිබ
    0.51
    مکمل
    0.49
    𝙩
    0.49
    禊
    0.48
     fiancé
    0.48
     bassist
    0.48
    ốp
    0.48
    憊
    0.48
    POSITIVE LOGITS
    可能
    0.58
     за
    0.55
     для
    0.54
    能
    0.54
     с
    0.52
    で
    0.51
     от
    0.49
     при
    0.49
    _
    0.49
     типа
    0.49
    Activations Density 0.000%

    No Known Activations