© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 1566
    Prev
    Next
    INDEX
    Explanations

    text input actions

    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_38_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
    wpt
    0.39
     embraced
    0.38
     soi
    0.37
     Strateg
    0.36
    enzi
    0.35
    乃
    0.35
     sanctioned
    0.34
    ことがあります
    0.34
    esprit
    0.34
    颯
    0.34
    POSITIVE LOGITS
    Text
    0.62
     Text
    0.62
     text
    0.59
    text
    0.52
     ٹیکسٹ
    0.49
     тек
    0.49
    Texts
    0.48
     Texts
    0.47
     texte
    0.47
     texts
    0.46
    Activations Density 0.017%

    No Known Activations