© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 203681
    Prev
    Next
    INDEX
    Explanations

    for yourself

    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_12_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
    拉
    0.60
    این
    0.59
     составе
    0.56
    この
    0.55
    того
    0.55
     acht
    0.55
    Ма
    0.55
    urusan
    0.54
     mismos
    0.53
    자는
    0.53
    POSITIVE LOGITS
     ù
    0.58
     û
    0.57
     -
    0.56
     –
    0.55
    ową
    0.55
     ->
    0.54
    ige
    0.53
     by
    0.52
     ü
    0.51
    ன்
    0.50
    Activations Density 0.003%

    No Known Activations