© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27694
    Prev
    Next
    INDEX
    Explanations

    keep up with

    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
    s
    0.40
    5
    0.39
    4
    0.39
    at
    0.38
    ：
    0.37
    2
    0.34
    ের
    0.33
    1
    0.33
    »
    0.32
    SC
    0.32
    POSITIVE LOGITS
     intervalles
    0.31
     ferrugineux
    0.30
     hız
    0.30
     végétaux
    0.30
     compleja
    0.29
     aplatis
    0.29
     anciens
    0.29
    其他
    0.29
     vitesse
    0.28
     vigueur
    0.28
    Activations Density 0.001%

    No Known Activations