© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 145792
    Prev
    Next
    INDEX
    Explanations

    image placeholders or links

    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_18_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
     E
    0.29
     T
    0.27
     CON
    0.26
     R
    0.26
     N
    0.26
     Não
    0.25
    ır
    0.25
     AH
    0.25
     M
    0.24
     AN
    0.24
    POSITIVE LOGITS
    डील
    0.27
    Rag
    0.24
    Regulation
    0.24
     tienen
    0.23
    LookAndFeel
    0.23
     зовут
    0.23
    色は
    0.23
    日在
    0.23
    ಾಗುತ್ತದೆ
    0.23
     हफ्ते
    0.22
    Activations Density 0.001%

    No Known Activations