© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 67469
    Prev
    Next
    INDEX
    Explanations

    Dub

    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_51_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
    ✵
    0.43
    び
    0.43
    ಮಂತ್ರಿ
    0.42
     Dubna
    0.41
    മ്പി
    0.40
     juni
    0.39
    мир
    0.38
     Juni
    0.38
     جما
    0.37
    াবি
    0.37
    POSITIVE LOGITS
    赛
    0.46
    賽
    0.44
    BEC
    0.42
    тельность
    0.41
     Cheval
    0.41
    ได
    0.41
    beck
    0.41
    gu
    0.40
    Chev
    0.40
    Schedule
    0.39
    Activations Density 0.000%

    No Known Activations