© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11274
    Prev
    Next
    INDEX
    Explanations

    bottomless / analyzed

    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
     dúvidas
    0.61
     армии
    0.58
     ද
    0.53
     অপেক্ষা
    0.53
     alguém
    0.52
     అవకాశ
    0.52
     государ
    0.51
     पुन्हा
    0.51
     været
    0.51
     perquè
    0.51
    POSITIVE LOGITS
     We
    0.63
    We
    0.52
    т
    0.52
     we
    0.50
    _
    0.50
     OW
    0.49
     Lorentzian
    0.49
     bird
    0.49
    ßt
    0.48
     Social
    0.48
    Activations Density 0.001%

    No Known Activations