© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 133349
    Prev
    Next
    INDEX
    Explanations

    master reference

    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_6_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
    もら
    1.01
    olutions
    0.92
    RUPTION
    0.91
    fficient
    0.89
    Were
    0.87
    highly
    0.87
    CLUSIVE
    0.86
    ﻓ
    0.86
    kitchen
    0.84
    million
    0.84
    POSITIVE LOGITS
    ă
    1.42
    ı
    1.40
     (
    1.39
    ы
    1.34
    ف
    1.26
    ne
    1.15
    ó
    1.13
    ut
    1.12
     was
    1.11
    ä
    1.09
    Activations Density 0.002%

    No Known Activations