© 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. 124117
    Prev
    Next
    INDEX
    Explanations

    action completion status

    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
     ജന
    0.42
     अवशेष
    0.41
    tabPadding
    0.40
     দাবী
    0.40
    Magnitude
    0.39
     voordat
    0.39
    輿
    0.39
    尒
    0.38
    बाई
    0.38
    鐸
    0.38
    POSITIVE LOGITS
     completely
    0.37
     sorry
    0.37
     playfully
    0.36
     ingl
    0.36
    亚马
    0.36
     playful
    0.35
     ing
    0.35
     lighter
    0.35
     thankful
    0.35
    ະ
    0.35
    Activations Density 0.007%

    No Known Activations