© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 209695
    Prev
    Next
    INDEX
    Explanations

    code loop iterators like `i`

    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_20_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
     দীপ
    0.44
     ω
    0.39
     읽
    0.37
     sebanyak
    0.37
    ᆨ
    0.36
     நிறை
    0.36
     dirinya
    0.36
     Ն
    0.35
     이어
    0.35
    該
    0.34
    POSITIVE LOGITS
    äs
    0.43
    \},\
    0.42
    racción
    0.40
    沍
    0.39
    clips
    0.39
    ologen
    0.39
    namespaces
    0.39
     Produktion
    0.39
    itzerland
    0.38
    orsunuz
    0.37
    Activations Density 0.004%

    No Known Activations