© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144740
    Prev
    Next
    INDEX
    Explanations

    gitlab configuration files

    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
    ド
    1.62
    ‌,
    1.41
    ла
    1.36
    ด
    1.36
    த
    1.34
    д
    1.33
    স
    1.33
    кта
    1.31
    ع
    1.27
    σ
    1.27
    POSITIVE LOGITS
    om
    1.73
    am
    1.68
     be
    1.54
    </h3>
    1.51
     de
    1.51
    ни
    1.42
    és
    1.40
    n
    1.40
    um
    1.38
    ación
    1.38
    Activations Density 0.000%

    No Known Activations