© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 129472
    Prev
    Next
    INDEX
    Explanations

    pronunciation guides

    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
     ہوگی
    0.47
    لوب
    0.46
    يير
    0.45
    ರಿಯ
    0.43
     reaper
    0.43
     coupon
    0.43
    ר
    0.43
    σια
    0.42
     لوبه
    0.42
    뇰
    0.42
    POSITIVE LOGITS
    \
    0.78
    -
    0.64
    st
    0.63
    j
    0.63
    1
    0.62
    v
    0.60
    k
    0.60
    ma
    0.58
    ies
    0.57
    d
    0.57
    Activations Density 0.002%

    No Known Activations