© 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. 9765
    Prev
    Next
    INDEX
    Explanations

    angle brackets that enclose HTML tags

    oai_token-act-pair · gemini-2.0-flash

    Less-than sign

    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
     k
    -0.62
     sp
    -0.60
     pla
    -0.58
     b
    -0.53
     tik
    -0.53
     aid
    -0.52
     q
    -0.51
     qu
    -0.51
     err
    -0.50
     t
    -0.49
    POSITIVE LOGITS
     Económica
    0.64
     Efq
    0.64
     fédé
    0.60
    Portale
    0.60
     chré
    0.58
    dyž
    0.56
     industriels
    0.55
     Shakspeare
    0.54
     Sociales
    0.52
     russes
    0.52
    Activations Density 0.554%

    No Known Activations