© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 206
    Prev
    Next
    INDEX
    Explanations

    strings related to scientific experiments and solutions

    oai_token-act-pair · gemini-2.0-flash

    laboratory reagents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     للاسماء
    -0.77
     كومونز
    -0.74
    CloseOperation
    -0.72
     EconPapers
    -0.68
     विश्वसनीयता
    -0.68
    webElementXpaths
    -0.67
     оригіналу
    -0.67
     EdgeInsets
    -0.67
    Péri
    -0.66
    InvalidProtocol
    -0.63
    POSITIVE LOGITS
    HomeAsUpEnabled
    0.52
     Nao
    0.44
    bleau
    0.42
     TAR
    0.41
    GINS
    0.40
    INGTON
    0.40
     tar
    0.40
    Suit
    0.39
    doPost
    0.39
     Tren
    0.39
    Activations Density 4.046%

    No Known Activations