© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 50946
    Prev
    Next
    INDEX
    Explanations

    the Trevor Project

    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
    Counsel
    0.40
     Maureen
    0.39
     जीनत
    0.37
     Diagnosis
    0.37
    コミュニ
    0.37
    Helen
    0.37
    Shannon
    0.36
    뮌
    0.36
     jurisprudence
    0.35
    Administ
    0.35
    POSITIVE LOGITS
    /*
    0.37
     capas
    0.37
     ('
    0.37
     (?
    0.36
     Recreational
    0.36
     ways
    0.36
     recreational
    0.36
     Gener
    0.35
    ('*
    0.35
     ಚಿ
    0.35
    Activations Density 0.003%

    No Known Activations