© 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. 196943
    Prev
    Next
    INDEX
    Explanations

    less than less than or equal

    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
    嗕
    0.56
    ن
    0.54
    مس
    0.51
    ماً
    0.49
    ٥
    0.49
    mniej
    0.48
    奔
    0.48
    正
    0.48
    동
    0.48
    疲
    0.48
    POSITIVE LOGITS
     (
    0.61
     acuity
    0.58
     prejudices
    0.47
     deforestation
    0.46
     צריך
    0.46
     expertise
    0.45
     eradicate
    0.45
     authorizations
    0.45
     ungraded
    0.45
     amuse
    0.45
    Activations Density 0.000%

    No Known Activations