© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 12060
    Prev
    Next
    INDEX
    Explanations

    sql column definitions

    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
     faço
    0.63
    郆
    0.63
     slecht
    0.52
     inú
    0.52
     numerosi
    0.51
     нада
    0.50
     obtem
    0.50
    <unused963>
    0.50
    вається
    0.49
    行业的
    0.49
    POSITIVE LOGITS
    th
    0.70
    ed
    0.70
    de
    0.66
    M
    0.61
    ie
    0.60
    ue
    0.56
    ko
    0.56
    Before
    0.56
    la
    0.56
    is
    0.55
    Activations Density 0.001%

    No Known Activations