© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 36119
    Prev
    Next
    INDEX
    Explanations

    national anthem

    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_31_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
    ору
    0.28
    PanelView
    0.28
    卩
    0.28
    geometric
    0.28
    ensch
    0.27
     직선
    0.27
     lateinit
    0.27
     geométricas
    0.27
    ucidation
    0.27
    蔑
    0.27
    POSITIVE LOGITS
    kurat
    0.32
    Anthony
    0.31
     Fert
    0.27
     Cá
    0.27
    various
    0.26
    Fert
    0.26
     unanticipated
    0.26
     ताल
    0.26
    curl
    0.26
     Minaj
    0.26
    Activations Density 0.000%

    No Known Activations