© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92188
    Prev
    Next
    INDEX
    Explanations

    Qu'est-ce que

    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_11_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
    iming
    0.63
    b
    0.62
    ä
    0.62
    f
    0.62
    av
    0.61
    bl
    0.57
    á
    0.56
    í
    0.56
    im
    0.55
    k
    0.54
    POSITIVE LOGITS
     significa
    0.59
     tarsi
    0.58
    その
    0.56
    Ŝ
    0.55
     deve
    0.54
    荕
    0.54
     trova
    0.54
     deren
    0.53
     efek
    0.53
     devono
    0.53
    Activations Density 0.000%

    No Known Activations