© 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. 14398
    Prev
    Next
    INDEX
    Explanations

    formatting and style commands, likely for code or image creation.

    oai_token-act-pair · gemini-2.0-flash

    Code and parameters descriptions

    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
    Tikang
    -0.71
     culturelles
    -0.61
    erals
    -0.59
    gameserver
    -0.58
     Paglinawan
    -0.58
    ⓧ
    -0.57
    gebob
    -0.56
    orteur
    -0.55
    utebol
    -0.55
     Housewives
    -0.55
    POSITIVE LOGITS
    JsonInclude
    0.44
    دانشنامهٔ
    0.42
    }*/
    0.41
     createContext
    0.40
     InputDecoration
    0.39
     @[
    0.39
    :]:
    0.39
     hiel
    0.38
    原始内容存档于
    0.38
    <![
    0.38
    Activations Density 6.254%

    No Known Activations