© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79905
    Prev
    Next
    INDEX
    Explanations

    una followed by a noun

    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_0_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
    中の
    1.68
    া
    1.60
    ंनी
    1.52
    用い
    1.49
    多い
    1.47
    ر
    1.45
    含む
    1.43
    ۵
    1.43
    ご紹介
    1.42
    お
    1.42
    POSITIVE LOGITS
    ين
    1.38
    s
    1.28
    ים
    1.24
    ská
    1.18
    ні
    1.16
    ach
    1.16
    ς
    1.15
    ла
    1.14
    를
    1.09
    å
    1.07
    Activations Density 0.003%

    No Known Activations