© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 163797
    Prev
    Next
    INDEX
    Explanations

    think of it like this:

    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_13_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
     ।*
    0.55
    िया
    0.55
     J
    0.54
    ot
    0.52
     L
    0.52
     Nuevo
    0.52
     Long
    0.51
     emulate
    0.51
     Lazar
    0.51
    }$
    0.50
    POSITIVE LOGITS
    quantitative
    0.57
     점에서
    0.55
    Maharashtra
    0.54
    年の
    0.54
    每年
    0.50
    variants
    0.49
     года
    0.48
     definitiva
    0.48
     کوئی
    0.47
    وڑ
    0.47
    Activations Density 0.004%

    No Known Activations