© 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-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3589
    Prev
    Next
    INDEX
    Explanations

    Devanagari script and Thai language text

    oai_token-act-pair · gemini-2.0-flash

    Foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beginnetje
    -1.06
     AspNetCore
    -1.05
     
    -1.04
     betweenstory
    -1.02
     
    -0.98
    UrlResolution
    -0.98
     
    -0.96
     TDA
    -0.95
    queryInterface
    -0.95
     Мексичка
    -0.95
    POSITIVE LOGITS
    ÁND
    0.47
     correspondance
    0.44
    write
    0.35
    icis
    0.35
    pæ
    0.34
     conva
    0.33
    ENTI
    0.33
     Entsch
    0.32
     is
    0.32
     comte
    0.32
    Activations Density 0.231%

    No Known Activations