© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9963
    Prev
    Next
    INDEX
    Explanations

    code snippets or mathematical/logical operations used in programming languages

    oai_token-act-pair · gemini-2.0-flash

    three

    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
     fifth
    -0.68
    Fifth
    -0.66
     Fifth
    -0.63
    fifth
    -0.62
    findpost
    -0.60
     ویکی‌پدیا
    -0.57
    第五
    -0.57
    Fourth
    -0.55
     Fourth
    -0.54
     quinto
    -0.53
    POSITIVE LOGITS
     Three
    1.60
     three
    1.55
    3
    1.53
    Three
    1.40
    three
    1.33
     trois
    1.27
     THREE
    1.24
    三
    1.20
    ３
    1.19
     três
    1.17
    Activations Density 23.653%

    No Known Activations