© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2126
    Prev
    Next
    INDEX
    Explanations

    lines of code with a lot of dots and the word 'import'

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ⓧ
    -0.52
    AutoresizingMask
    -0.50
     Gar
    -0.47
     Ball
    -0.47
     Bag
    -0.46
     Bur
    -0.46
     Ad
    -0.46
     Ba
    -0.45
     BFS
    -0.44
     Bar
    -0.44
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.43
    feira
    0.39
    ail
    0.39
    ek
    0.39
    haupt
    0.38
    owieck
    0.36
     jLabel
    0.36
    aren
    0.35
    ele
    0.35
    eb
    0.34
    Activations Density 3.287%

    No Known Activations