© 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. 5892
    Prev
    Next
    INDEX
    Explanations

    code from computer programs

    oai_token-act-pair · gemini-2.0-flash

    code and logs

    np_max-act-logits · 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
     CreateTagHelper
    -1.57
     propOrder
    -1.48
     Paglinawan
    -1.36
     ainfi
    -1.27
     nakalista
    -1.27
     فريبيس
    -1.27
    DockStyle
    -1.23
     '\\;'
    -1.23
    InjectAttribute
    -1.22
     betweenstory
    -1.22
    POSITIVE LOGITS
     
    1.02
    :
    0.87
    .
    0.86
    ,
    0.82
     in
    0.78
     is
    0.78
    ...
    0.75
     ...
    0.72
     di
    0.71
     at
    0.69
    Activations Density 11.279%

    No Known Activations