© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12325
    Prev
    Next
    INDEX
    Explanations

    the words "junior", "senior", "Sim" and quadrilaterals relating to high school and sports

    oai_token-act-pair · gemini-2.0-flash

    junior or quad

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     contrary
    -0.52
     vétérina
    -0.52
    //</
    -0.51
    <eos>
    -0.51
     phù
    -0.49
    igshid
    -0.49
     flèche
    -0.48
     way
    -0.48
     myö
    -0.47
     EnglishChoose
    -0.47
    POSITIVE LOGITS
    MessageTagHelper
    0.85
    ніципалі
    0.76
    ագրություններ
    0.76
    DoubleQuotes
    0.75
    amerikanischer
    0.73
    modelBuilder
    0.71
    LabelTagHelper
    0.71
    UserScript
    0.69
    ՚
    0.68
    يكب
    0.67
    Activations Density 0.454%

    No Known Activations