© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 100143
    Prev
    Next
    INDEX
    Explanations

    artisan make:migration

    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_16_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
    𝔦
    0.52
     Observations
    0.48
    ંત્ર
    0.46
     домаћинства
    0.46
    "]:
    0.45
    感想
    0.45
     irrational
    0.44
     deviations
    0.44
     オレンジ
    0.44
    }+\
    0.43
    POSITIVE LOGITS
    has
    0.54
     خات
    0.48
    isEmpty
    0.47
    يا
    0.45
    െ
    0.44
    does
    0.43
     العالم
    0.42
     كريم
    0.42
    EW
    0.42
     заместитель
    0.42
    Activations Density 0.000%

    No Known Activations