© 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. 77989
    Prev
    Next
    INDEX
    Explanations

    less, lowest, weak

    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
     높은
    0.46
    高い
    0.45
     υψη
    0.44
    ymax
    0.43
     vysok
    0.41
     høj
    0.41
    မြင့်
    0.40
    亢
    0.40
     høy
    0.39
    更高
    0.39
    POSITIVE LOGITS
     low
    0.65
     lowered
    0.61
     lowest
    0.60
    低
    0.60
     Low
    0.58
     低
    0.58
     (<
    0.57
     lowers
    0.57
     lower
    0.56
     diminished
    0.54
    Activations Density 0.024%

    No Known Activations