© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 65427
    Prev
    Next
    INDEX
    Explanations

    premium surcharge

    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_41_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
     WO
    0.44
    pathTemplates
    0.42
    hitth
    0.39
    Ｏ
    0.39
     O
    0.38
     집에
    0.38
    ஓ
    0.38
    껐
    0.36
    etano
    0.36
    eyim
    0.36
    POSITIVE LOGITS
     supplement
    1.01
     supplements
    0.93
     surcharge
    0.91
     suplement
    0.89
     Supplement
    0.87
    Supplement
    0.87
     premiums
    0.81
     Zusch
    0.77
     SUPPLEMENT
    0.77
    supplement
    0.76
    Activations Density 0.028%

    No Known Activations