© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13601
    Prev
    Next
    INDEX
    Explanations

    alcohol consumption, airport, nitrogen oxides

    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_13_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
     L
    0.46
     in
    0.45
     uplifting
    0.43
     جست
    0.40
    קט
    0.40
     Bioinformatics
    0.40
     emf
    0.39
     enumeration
    0.39
     Genealogical
    0.39
     agarose
    0.38
    POSITIVE LOGITS
     функцию
    0.48
     Choibalsan
    0.48
    ㄑ
    0.46
    blue
    0.45
     ہماری
    0.45
    贰
    0.43
    Pierre
    0.42
    ਤੇ
    0.42
     ૩
    0.42
    酗
    0.42
    Activations Density 0.026%

    No Known Activations