© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173270
    Prev
    Next
    INDEX
    Explanations

    select option or function

    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
    www
    0.44
    了很多
    0.44
     lubricants
    0.42
    （
    0.42
    마
    0.40
    และ
    0.40
    ポーツ
    0.38
    ਾਰੇ
    0.38
    ”（
    0.38
    ส
    0.37
    POSITIVE LOGITS
     выборах
    0.48
     システム
    0.46
    𒊏
    0.45
     nossas
    0.45
     Cho
    0.44
    Quit
    0.42
    ACON
    0.41
     Насе
    0.41
     ezingu
    0.41
     przyję
    0.41
    Activations Density 0.000%

    No Known Activations