© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 227559
    Prev
    Next
    INDEX
    Explanations

    Baudr or DR followed by numbers

    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_6_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
    1.15
    上
    1.03
    น
    0.92
    n
    0.91
     handyman
    0.90
     diner
    0.86
     decid
    0.86
    มัน
    0.86
    y
    0.85
     halibut
    0.84
    POSITIVE LOGITS
    ↵
    1.19
    extrait
    1.15
    ation
    1.12
    industry
    1.09
    ave
    1.05
    kerja
    1.04
    identification
    1.04
    he
    1.03
    queries
    1.03
    renzia
    1.02
    Activations Density 0.000%

    No Known Activations