© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 15564
    Prev
    Next
    INDEX
    Explanations

    Boston Globe

    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_34_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
     অক্স
    0.38
     arises
    0.38
     finishes
    0.37
     Gra
    0.37
    мпа
    0.36
    话说
    0.36
    ృ
    0.36
     অনিশ্চ
    0.35
     highlights
    0.35
     infin
    0.35
    POSITIVE LOGITS
    Boston
    0.49
     Boston
    0.46
     Instrumented
    0.38
     muscular
    0.37
     boston
    0.36
    (($
    0.36
    眇
    0.36
    boston
    0.36
    Banking
    0.35
     ставкалары
    0.35
    Activations Density 0.003%

    No Known Activations