© 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. 1569
    Prev
    Next
    INDEX
    Explanations

    instances the word 'throw' is used, together with related words and context

    oai_token-act-pair · gemini-2.0-flash

    code exceptions

    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
     throw
    -2.95
     thrown
    -2.88
     throwing
    -2.77
     threw
    -2.69
     Throw
    -2.67
     throws
    -2.61
    throw
    -2.50
     Throwing
    -2.50
    Throw
    -2.48
    throwing
    -2.28
    POSITIVE LOGITS
    ocere
    0.48
     Antal
    0.45
     Renaud
    0.44
    ModelBuilder
    0.44
     Nowak
    0.43
    medad
    0.43
    seat
    0.43
    Sunt
    0.43
    rät
    0.42
    
    0.42
    Activations Density 2.516%

    No Known Activations