© 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. 194890
    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
    ◣
    0.39
    وما
    0.36
     सब्जी
    0.36
    当量
    0.35
     Ceux
    0.35
     टाइम
    0.35
     निजा
    0.35
     możesz
    0.35
     paff
    0.35
    峤
    0.35
    POSITIVE LOGITS
     superiors
    0.44
    GREES
    0.40
    ളി
    0.35
    選択
    0.35
    ട്ടുണ്ട്
    0.34
    សំណ
    0.33
    él
    0.33
     まし
    0.33
    ́a
    0.33
    lays
    0.33
    Activations Density 0.000%

    No Known Activations