© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14931
    Prev
    Next
    INDEX
    Explanations

    LaTeX and HTML markup code

    oai_token-act-pair · gemini-2.0-flash

    code and reports

    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
    iz
    -0.57
     Magdalen
    -0.57
    ly
    -0.56
    ha
    -0.55
    už
    -0.54
    ab
    -0.52
     Radha
    -0.52
    é
    -0.52
    ed
    -0.51
     있
    -0.51
    POSITIVE LOGITS
     Dodo
    0.86
     Klee
    0.83
     Arora
    0.80
     Sidd
    0.80
     Garr
    0.79
     Sando
    0.77
     Keene
    0.76
     Papi
    0.75
     defStyle
    0.75
     Satt
    0.73
    Activations Density 6.753%

    No Known Activations