© 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. 1822
    Prev
    Next
    INDEX
    Explanations

    javascript code with specific syntax

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    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
     ainfi
    -0.71
    berdayakan
    -0.71
     définiti
    -0.68
     quelcon
    -0.66
     colorés
    -0.66
     feroit
    -0.64
    antaranya
    -0.63
    rungsseite
    -0.63
     industriels
    -0.63
    ...');
    -0.62
    POSITIVE LOGITS
     
    0.47
     has
    0.45
    to
    0.41
     is
    0.41
     safety
    0.40
     safe
    0.38
     as
    0.38
     lob
    0.37
     star
    0.37
     data
    0.36
    Activations Density 5.023%

    No Known Activations