© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 195909
    Prev
    Next
    INDEX
    Explanations

    condor methods, or variables

    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_4_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
    í
    1.23
    é
    1.01
    s
    0.99
    k
    0.95
    á
    0.90
    ي
    0.89
     VFX
    0.88
    sü
    0.88
    n
    0.88
    )$.
    0.87
    POSITIVE LOGITS
    0
    0.95
    ing
    0.92
    फारिश
    0.91
    1
    0.85
    ais
    0.80
    는
    0.78
    amini
    0.77
    5
    0.76
    ิน
    0.74
    ัน
    0.73
    Activations Density 0.001%

    No Known Activations