© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 149860
    Prev
    Next
    INDEX
    Explanations

    years followed by punctuation

    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_23_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
    vino
    0.42
     संबंध
    0.41
    ✺
    0.39
     आधा
    0.39
    udel
    0.38
    コント
    0.37
     }^{-
    0.36
    custList
    0.36
    relation
    0.36
    zmq
    0.36
    POSITIVE LOGITS
     oferecer
    0.48
     людей
    0.46
     ডি
    0.45
    ಾಗ
    0.43
     lidí
    0.43
    腑
    0.42
     людям
    0.42
     робити
    0.41
     Søren
    0.41
     ചെയ്യുന്നു
    0.41
    Activations Density 0.002%

    No Known Activations