© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 203707
    Prev
    Next
    INDEX
    Explanations

    liquids and ingredients quantities

    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_37_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
    ब्रे
    0.39
    ುವ
    0.38
     сове
    0.37
    Structural
    0.37
    ឈ
    0.35
     जाने
    0.35
    ParallelGroup
    0.35
    屹
    0.35
    хе
    0.34
    ippers
    0.34
    POSITIVE LOGITS
     Capacity
    0.82
     capacity
    0.77
     CAPACITY
    0.75
    capacity
    0.73
    Capacity
    0.72
     competency
    0.71
     incapacity
    0.67
     capacidad
    0.66
     capacité
    0.65
     Capac
    0.65
    Activations Density 0.002%

    No Known Activations