© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123400
    Prev
    Next
    INDEX
    Explanations

    Gulf of

    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
     serão
    0.71
     município
    0.64
     swimmers
    0.63
     municípios
    0.63
     votos
    0.62
     Física
    0.62
    у
    0.61
    ある
    0.61
    șa
    0.61
     Produto
    0.61
    POSITIVE LOGITS
    omme
    0.62
    om
    0.61
    by
    0.60
    ed
    0.57
    ic
    0.56
    at
    0.56
    ommen
    0.56
     introdu
    0.55
    7
    0.55
    ock
    0.54
    Activations Density 0.000%

    No Known Activations