© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 361
    Prev
    Next
    INDEX
    Explanations

    swift code keywords

    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
    dsp
    0.41
     conceitos
    0.40
    aleb
    0.38
    тельству
    0.37
    概念
    0.36
    дик
    0.35
    恜
    0.35
    ◹
    0.34
     concepts
    0.34
     symbolName
    0.34
    POSITIVE LOGITS
     barrier
    0.50
     barriers
    0.47
    barrier
    0.46
     Barrier
    0.44
     محور
    0.43
    Barrier
    0.41
    障碍
    0.40
     axis
    0.40
    奬
    0.39
     REN
    0.39
    Activations Density 0.005%

    No Known Activations