© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81350
    Prev
    Next
    INDEX
    Explanations

    fielder

    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_0_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
    н
    1.55
    '
    1.30
    те
    1.30
    ти
    1.29
    N
    1.21
    น
    1.20
    д
    1.16
    亍
    1.16
    ла
    1.16
    ето
    1.16
    POSITIVE LOGITS
     to
    1.31
    +\
    1.27
     evalu
    1.19
     organis
    1.19
     infest
    1.16
    ,\
    1.16
     irradi
    1.15
     infus
    1.15
     assimil
    1.13
    1
    1.12
    Activations Density 0.001%

    No Known Activations