© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27045
    Prev
    Next
    INDEX
    Explanations

    dominant words

    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_10_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
    AN
    0.32
    EL
    0.31
    WL
    0.30
    V
    0.29
    IS
    0.28
     архіви
    0.27
    AR
    0.26
    ER
    0.26
    डब्ल्यू
    0.26
    CH
    0.26
    POSITIVE LOGITS
    し
    0.29
    <strong>
    0.26
    非常に
    0.24
     cigarette
    0.24
    the
    0.24
    by
    0.23
     positiva
    0.23
    خ
    0.23
    っ
    0.23
    ти
    0.23
    Activations Density 0.012%

    No Known Activations