© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 108913
    Prev
    Next
    INDEX
    Explanations

    code syntax separators

    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_1_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
    ু
    1.59
    t
    1.41
    is
    1.36
    ک
    1.35
    will
    1.29
    સ
    1.23
    یک
    1.17
    ه
    1.17
    ா
    1.17
    f
    1.16
    POSITIVE LOGITS
    ك
    1.09
     be
    1.09
    га
    0.93
    ы
    0.91
    ка
    0.91
    е
    0.91
    gruppe
    0.89
    值
    0.88
     was
    0.88
    流畅
    0.83
    Activations Density 0.000%

    No Known Activations