© 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. 27274
    Prev
    Next
    INDEX
    Explanations

    head followed by descriptions

    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
     a
    0.27
    ع
    0.26
     you
    0.25
     \
    0.24
     een
    0.24
    H
    0.24
    स
    0.24
    ik
    0.24
    س
    0.23
    ش
    0.23
    POSITIVE LOGITS
    τή
    0.25
    inces
    0.20
     casque
    0.19
    तों
    0.19
    txn
    0.18
    த்தில்
    0.18
     ನಿಜ
    0.18
    jih
    0.18
    쥐
    0.18
    ής
    0.18
    Activations Density 0.008%

    No Known Activations