© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92259
    Prev
    Next
    INDEX
    Explanations

    currency control

    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_11_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
    5
    0.55
    (),
    0.53
    4
    0.52
    ad
    0.52
    9
    0.52
    br
    0.51
    6
    0.49
    trials
    0.48
    id
    0.47
    iv
    0.46
    POSITIVE LOGITS
     getBitmap
    0.56
     SRS
    0.54
     Bats
    0.52
     കൂടുതല്‍
    0.52
    鷸
    0.51
     Gä
    0.50
     ആരോഗ്യ
    0.50
     Wanda
    0.49
     रोग
    0.49
     Penelope
    0.48
    Activations Density 0.000%

    No Known Activations