© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86212
    Prev
    Next
    INDEX
    Explanations

    john [surname]

    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
    𝒹
    0.54
     fable
    0.54
    扨
    0.54
     fad
    0.52
    ண்ண
    0.50
    ജാ
    0.49
    কি
    0.49
     enam
    0.48
    𝓭
    0.48
     curiosity
    0.48
    POSITIVE LOGITS
    h
    0.74
    s
    0.73
    u
    0.72
    é
    0.66
    (
    0.64
    á
    0.61
    z
    0.60
    ina
    0.59
    的关键
    0.55
    ل
    0.55
    Activations Density 0.000%

    No Known Activations