© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130872
    Prev
    Next
    INDEX
    Explanations

    go standard library imports

    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_6_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
    \
    1.53
    <
    1.34
    IS
    1.27
    """
    1.16
    é
    1.16
    [
    1.15
    ne
    1.09
    í
    1.09
    Š
    1.09
    '
    1.08
    POSITIVE LOGITS
    ного
    1.06
     человеком
    0.97
     foggy
    0.94
     desolate
    0.94
    အစိတ်အပိုင်း
    0.94
    <unused254>
    0.90
    ных
    0.89
    никами
    0.88
     vijj
    0.88
     uczni
    0.88
    Activations Density 0.001%

    No Known Activations