© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 88652
    Prev
    Next
    INDEX
    Explanations

    I was thinking

    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_18_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
     personnel
    0.52
    (\
    0.52
    (
    0.51
     biolog
    0.50
    I
    0.50
     degrees
    0.50
     reporting
    0.50
     levels
    0.49
    (&
    0.49
    In
    0.49
    POSITIVE LOGITS
    hashMap
    0.48
     Glück
    0.47
    ्योपै
    0.46
     Syrup
    0.46
    мок
    0.46
     словами
    0.46
     Verständ
    0.45
    酊
    0.45
    蓯
    0.45
    addies
    0.44
    Activations Density 0.004%

    No Known Activations