© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 197658
    Prev
    Next
    INDEX
    Explanations

    numeric literal or code snippets

    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_15_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
    s
    0.73
    on
    0.66
    r
    0.61
    p
    0.59
    app
    0.58
    z
    0.57
    هم
    0.55
    ons
    0.54
    n
    0.53
    par
    0.52
    POSITIVE LOGITS
     cityName
    0.63
     putih
    0.60
     drugih
    0.54
     fiume
    0.54
     riječ
    0.53
     macchina
    0.53
     Bạch
    0.52
     použ
    0.52
    dropPanel
    0.52
     реки
    0.50
    Activations Density 0.000%

    No Known Activations