© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164846
    Prev
    Next
    INDEX
    Explanations

    dosage units and concentrations

    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_31_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
    ≔
    0.33
    clinical
    0.28
     клини
    0.28
    generators
    0.28
    而后
    0.28
    škai
    0.27
    ira
    0.27
     clinically
    0.27
    чені
    0.27
    ../
    0.26
    POSITIVE LOGITS
     rilas
    0.34
     kapasitas
    0.33
    Capacity
    0.32
     capacity
    0.32
    닥
    0.31
    فك
    0.31
    每天
    0.31
    Shake
    0.31
    اتج
    0.30
    Thoughts
    0.30
    Activations Density 0.000%

    No Known Activations