© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10627
    Prev
    Next
    INDEX
    Explanations

    code snippets, website URLs, and related code and licensing terms

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
    ,
    -0.85
    .
    -0.84
     
    -0.83
    ↵
    -0.83
    <unused62>
    -0.79
    Ã
    -0.79
    <unused63>
    -0.79
    <unused61>
    -0.78
     (
    -0.78
     and
    -0.75
    POSITIVE LOGITS
     étoient
    0.73
     avoient
    0.68
     Theſe
    0.64
     Efq
    0.63
     varandra
    0.58
     themſelves
    0.57
     feroit
    0.56
     becauſe
    0.56
     purpoſe
    0.56
     stället
    0.56
    Activations Density 4.446%

    No Known Activations