© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18763
    Prev
    Next
    INDEX
    Explanations

    kotlin code examples

    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_40_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
    Internet
    0.42
    互联网
    0.41
    OpenJDK
    0.40
    杭
    0.40
    сок
    0.39
    甾
    0.39
    Repository
    0.38
    internet
    0.37
    Modular
    0.36
     г
    0.36
    POSITIVE LOGITS
     spectrum
    0.45
    aysia
    0.43
     decon
    0.43
     shuffling
    0.41
     Shr
    0.40
    ogat
    0.40
     Abdullah
    0.38
     Shams
    0.38
     allocator
    0.38
     sondern
    0.38
    Activations Density 0.046%

    No Known Activations