© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 158644
    Prev
    Next
    INDEX
    Explanations

    Aerion, dragons, nobility

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    テール
    0.41
    hal
    0.41
    哲学
    0.41
     filoz
    0.41
    хал
    0.40
    ifik
    0.40
    ئ
    0.39
    綏
    0.39
    ilos
    0.38
    尒
    0.38
    POSITIVE LOGITS
     Latvian
    0.43
    を経て
    0.41
     Latham
    0.41
     Latvia
    0.40
     Hend
    0.40
     Belg
    0.40
     legends
    0.40
     Vaughan
    0.39
    Hend
    0.38
     Chesterfield
    0.38
    Activations Density 0.007%

    No Known Activations