© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 208186
    Prev
    Next
    INDEX
    Explanations

    quantify achievements

    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_19_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
    ーク
    0.45
     jah
    0.45
     olnud
    0.42
    올
    0.41
     gewesen
    0.41
     overtaking
    0.41
     skiers
    0.40
     avait
    0.39
     deng
    0.38
     yow
    0.38
    POSITIVE LOGITS
     settles
    0.55
     won
    0.54
     then
    0.54
     coveted
    0.52
     will
    0.50
     threw
    0.47
     પછી
    0.47
     C
    0.46
     ущер
    0.46
    цева
    0.46
    Activations Density 0.003%

    No Known Activations