© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 65659
    Prev
    Next
    INDEX
    Explanations

    foreign characters

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_51_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
    v
    0.72
    ਵ
    0.66
    vus
    0.62
    ви
    0.61
    𝑣
    0.61
    ्व
    0.59
    vió
    0.59
    vní
    0.58
    ্ব
    0.57
    𝘃
    0.57
    POSITIVE LOGITS
    盧
    0.40
    卢
    0.39
    ych
    0.38
    стро
    0.38
    ချင်း
    0.37
    chn
    0.37
     Нет
    0.37
    मनी
    0.36
    rique
    0.36
    QUIN
    0.36
    Activations Density 0.000%

    No Known Activations