© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35023
    Prev
    Next
    INDEX
    Explanations

    SVP / VP / BP phrases

    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_3_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
    f
    1.11
     and
    0.97
    b
    0.96
    ↵↵
    0.94
    ↵
    0.91
    K
    0.86
     have
    0.84
    V
    0.84
    have
    0.82
    be
    0.80
    POSITIVE LOGITS
    쐞
    0.92
     fabriqu
    0.89
     financiera
    0.83
     traditionnelle
    0.82
     comedor
    0.80
     pequeno
    0.79
     tigre
    0.79
     Reforma
    0.78
    쯜
    0.78
     controlador
    0.77
    Activations Density 0.003%

    No Known Activations