© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 166558
    Prev
    Next
    INDEX
    Explanations

    plus interest on overdue amounts

    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_34_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
     maximizes
    0.43
     %[
    0.42
     maximize
    0.40
     queues
    0.40
     Cn
    0.38
     saves
    0.38
     %\
    0.37
     identifications
    0.36
     productive
    0.36
    Banking
    0.36
    POSITIVE LOGITS
    に応
    0.49
    zw
    0.41
     unlimited
    0.39
     அதற்கு
    0.38
     Unlimited
    0.38
    附加
    0.37
    [-\
    0.36
    カウント
    0.36
     응
    0.35
    Ӣ
    0.35
    Activations Density 0.002%

    No Known Activations