© 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. 48763
    Prev
    Next
    INDEX
    Explanations

    ) Based, development, funding

    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
    ↵
    1.45
    :
    1.39
     I
    1.31
    '
    1.31
    -
    1.20
    ী
    1.09
    ת
    1.07
    /
    1.06
    .
    1.05
    ة
    1.01
    POSITIVE LOGITS
    of
    1.41
    agamanam
    1.20
     of
    1.15
     a
    1.08
    aj
    1.00
    s
    1.00
    stopping
    0.98
    number
    0.97
    instance
    0.97
    浧
    0.95
    Activations Density 0.043%

    No Known Activations