© 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. 13396
    Prev
    Next
    INDEX
    Explanations

    words ending in suffixes like -ene, -ol, -al, -it, -ent, and prefixes like re-.

    oai_token-act-pair · gemini-2.0-flash

    word parts

    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
    出版年
    -0.54
     ivelany
    -0.53
    原始内容存档于
    -0.50
     navires
    -0.47
     exercise
    -0.46
    BeginContext
    -0.46
     boî
    -0.45
     earthquake
    -0.45
     leçons
    -0.45
     ModelExpression
    -0.44
    POSITIVE LOGITS
     Salts
    0.62
     Pits
    0.61
    rics
    0.57
     onOptions
    0.57
    props
    0.56
    Parms
    0.56
    IGraphics
    0.56
     Scripts
    0.55
    params
    0.54
    MISSIONS
    0.54
    Activations Density 15.088%

    No Known Activations