© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60134
    Prev
    Next
    INDEX
    Explanations

    non-fungible tokens

    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
    er
    0.80
    0
    0.80
    on
    0.77
    are
    0.70
    0.63
    an
    0.63
    image
    0.62
    6
    0.61
    rich
    0.61
    ler
    0.60
    POSITIVE LOGITS
     rightly
    0.68
     justly
    0.66
    폼
    0.61
     gobiernos
    0.61
     Regierung
    0.60
    ᥙ
    0.59
     geopol
    0.58
     governments
    0.57
    ั
    0.57
    скоп
    0.56
    Activations Density 0.000%

    No Known Activations