© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5583
    Prev
    Next
    INDEX
    Explanations

    Rhonda Byrne, Ronda Rousey, Rhode Island, road

    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_39_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
     வயது
    0.40
    Schedule
    0.39
    衆
    0.39
     Schedule
    0.39
    Director
    0.38
    জিত
    0.38
    AGING
    0.36
    まさ
    0.36
     normally
    0.36
     শক্তি
    0.36
    POSITIVE LOGITS
    唪
    0.43
     forêts
    0.41
     kalam
    0.38
     zain
    0.37
    ｪ
    0.37
     fuori
    0.36
     Chac
    0.36
    ែម
    0.36
    unable
    0.35
     فهر
    0.35
    Activations Density 0.021%

    No Known Activations