© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 28501
    Prev
    Next
    INDEX
    Explanations

    exceptional situations

    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
     έχει
    0.43
    <unused1886>
    0.42
     виды
    0.42
     arquitect
    0.42
    чиго
    0.42
     Tử
    0.41
    ться
    0.40
    कियों
    0.40
    ಿಗಳು
    0.40
    ляти
    0.40
    POSITIVE LOGITS
    .
    0.55
    s
    0.51
    The
    0.49
    yr
    0.45
    6
    0.43
    r
    0.42
    '
    0.42
    ’
    0.41
    5
    0.41
    ط
    0.41
    Activations Density 0.025%

    No Known Activations