© 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. 33569
    Prev
    Next
    INDEX
    Explanations

    cooking instructions (duration)

    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
    ന്റ്
    0.42
    getLast
    0.42
    曇
    0.40
     dispensary
    0.40
     februari
    0.38
     februar
    0.38
     बुरा
    0.37
     beruf
    0.37
     प्रवासी
    0.36
    aliya
    0.36
    POSITIVE LOGITS
     ASPECTS
    0.43
    ܠ
    0.39
     hexagons
    0.39
     Speak
    0.38
    ವಹ
    0.38
     MANAGEMENT
    0.36
     तब्
    0.35
    quard
    0.34
     لمدة
    0.34
     Aspects
    0.34
    Activations Density 0.009%

    No Known Activations