© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6603
    Prev
    Next
    INDEX
    Explanations

    snippets from Japanese programming questions and code

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     my
    -0.82
     the
    -0.66
     Your
    -0.65
     I
    -0.62
     your
    -0.61
     You
    -0.61
     min
    -0.61
    ，
    -0.59
     of
    -0.59
    Czytaj
    -0.59
    POSITIVE LOGITS
     ALR
    0.70
     kaarangay
    0.68
     cdti
    0.66
     Sopho
    0.65
     fhew
    0.65
     PDI
    0.65
     NPA
    0.64
     FAP
    0.64
    Rhestr
    0.64
     eiffel
    0.64
    Activations Density 0.449%

    No Known Activations