© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 197337
    Prev
    Next
    INDEX
    Explanations

    BAD NOTGOOD, Peli Peli

    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
    tt
    0.61
    ud
    0.59
    ut
    0.59
    ط
    0.56
    其他
    0.55
    uves
    0.55
    ug
    0.54
    Ear
    0.54
    za
    0.54
     Star
    0.54
    POSITIVE LOGITS
     west
    0.61
     domains
    0.60
     교통
    0.60
    𝚎
    0.59
     route
    0.58
     Держа
    0.57
     domain
    0.56
     metropolitan
    0.56
     soothing
    0.56
     from
    0.55
    Activations Density 0.000%

    No Known Activations