© 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. 162430
    Prev
    Next
    INDEX
    Explanations

    accessible by

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Farland
    0.29
    迪士
    0.29
    ymmetry
    0.28
    cemia
    0.28
     visto
    0.28
    cant
    0.28
    싱
    0.27
    teness
    0.27
    दून
    0.27
     চিত্রক
    0.27
    POSITIVE LOGITS
     প্রতিযোগিতা
    0.30
     заклад
    0.30
     quest
    0.27
     overnight
    0.27
    ])).
    0.27
     Turnbull
    0.27
     competition
    0.27
     रिक्वेस्ट
    0.27
     tach
    0.27
     MAKEINTRESOURCE
    0.27
    Activations Density 0.003%

    No Known Activations