© 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. 33588
    Prev
    Next
    INDEX
    Explanations

    date advice

    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
     fraternity
    0.42
     ga
    0.39
     fxaa
    0.39
     closes
    0.39
    uales
    0.39
    ාවිත
    0.37
     洋
    0.37
     triumphant
    0.36
     vanqu
    0.36
    सेच
    0.36
    POSITIVE LOGITS
    দিকে
    0.44
     sensitized
    0.38
    家
    0.38
     Immunity
    0.37
    ێر
    0.37
    rabbit
    0.36
     horas
    0.36
     pomeriggio
    0.36
    EPS
    0.35
     insulted
    0.35
    Activations Density 0.015%

    No Known Activations