© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2847
    Prev
    Next
    INDEX
    Explanations

    welcome package or onboarding

    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_40_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
    BMI
    0.38
    нению
    0.38
    ឥ
    0.36
    biz
    0.35
     căn
    0.34
     Individuals
    0.34
     UTM
    0.34
    劶
    0.34
    珴
    0.34
     Muller
    0.33
    POSITIVE LOGITS
     onboard
    2.58
     aboard
    2.39
    aboard
    1.68
     bordo
    1.40
     board
    1.18
    board
    1.12
     बोर्ड
    1.05
     boarded
    1.01
    搭
    1.00
     탑
    0.96
    Activations Density 0.100%

    No Known Activations