© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 195991
    Prev
    Next
    INDEX
    Explanations

    number lists

    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_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
    ategorie
    0.42
    蛎
    0.40
    Ⴚ
    0.40
     मेमोरी
    0.39
     powierzchn
    0.38
    médiaire
    0.38
    हुन्छ
    0.38
    CurrentImageData
    0.38
     veineux
    0.38
    怸
    0.38
    POSITIVE LOGITS
    Aspect
    0.42
    Author
    0.40
    Transform
    0.37
    Rol
    0.37
     rolling
    0.37
     beat
    0.36
     rolled
    0.35
    Al
    0.35
    0.35
     geen
    0.35
    Activations Density 0.000%

    No Known Activations