© 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. 5649
    Prev
    Next
    INDEX
    Explanations

    the substring "Gar"

    oai_token-act-pair · gemini-2.0-flash

    Gar

    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
    DataSource
    -0.51
     ing
    -0.49
     Durand
    -0.48
    StatusCode
    -0.48
    PathParam
    -0.47
     College
    -0.47
    EXPR
    -0.46
    ör
    -0.46
     non
    -0.46
    celi
    -0.46
    POSITIVE LOGITS
    TagMode
    0.71
    énario
    0.69
     propOrder
    0.69
     @"/
    0.69
    WriteTagHelper
    0.68
    aarrggbb
    0.66
    HtmlAttribute
    0.65
     saites
    0.63
     defaultstate
    0.63
    InputTagHelper
    0.63
    Activations Density 0.489%

    No Known Activations