© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 61062
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     real
    0.88
     реа
    0.81
    实
    0.78
    real
    0.71
    実
    0.70
     रियल
    0.61
     实
    0.59
     실
    0.58
     réel
    0.56
     वास्तविक
    0.53
    POSITIVE LOGITS
     tell
    0.73
     telling
    0.67
     Tell
    0.66
    tell
    0.66
     TELL
    0.65
    telling
    0.61
    Tell
    0.57
     tells
    0.55
     True
    0.54
    告訴
    0.51
    Activations Density 0.002%

    No Known Activations