© 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. 15631
    Prev
    Next
    INDEX
    Explanations

    the word "feet" and words related to it, along with percentage and monetary words.

    oai_token-act-pair · gemini-2.0-flash

    feet

    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
     Völ
    -0.60
     voeten
    -0.50
     Albe
    -0.50
    Canon
    -0.49
    א
    -0.47
    my
    -0.47
    pages
    -0.47
     décrire
    -0.46
     mélanger
    -0.45
    授
    -0.45
    POSITIVE LOGITS
     EconPapers
    0.91
     initComponents
    0.78
    DoubleQuotes
    0.74
    HasForeignKey
    0.71
    tagHelperRunner
    0.71
    InitStruct
    0.70
    يميديا
    0.70
     GetEnumerator
    0.69
     defaultstate
    0.69
    ArrowToggle
    0.68
    Activations Density 2.619%

    No Known Activations