© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59918
    Prev
    Next
    INDEX
    Explanations

    closing brackets and code endings

    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_2_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
    at
    1.75
    ح
    1.49
    as
    1.48
    ла
    1.47
    ро
    1.44
    리
    1.43
    ന
    1.41
    .
    1.41
    ни
    1.40
    ного
    1.40
    POSITIVE LOGITS
     \
    1.26
     I
    0.99
     and
    0.95
    ting
    0.93
     was
    0.91
    mann
    0.87
    sin
    0.83
    s
    0.80
     And
    0.79
    ेन्द्र
    0.79
    Activations Density 0.000%

    No Known Activations