© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 77816
    Prev
    Next
    INDEX
    Explanations

    img src

    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_31_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
     Bulld
    0.40
    fieldContext
    0.39
     serm
    0.37
    ন্ত্রণাল
    0.37
    ክት
    0.37
    이라고
    0.36
    ным
    0.36
    说
    0.36
     им
    0.36
     apparent
    0.35
    POSITIVE LOGITS
    READY
    0.37
    owers
    0.37
    Dreams
    0.36
     READY
    0.35
    Led
    0.35
    vai
    0.35
     DAMAGES
    0.34
     კიდ
    0.34
     Mendez
    0.34
    LED
    0.33
    Activations Density 0.001%

    No Known Activations