© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 11002
    Prev
    Next
    INDEX
    Explanations

    c code function definitions usually including the word "probe"

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
     '\\;'
    -0.69
     "
    -0.60
    migrationBuilder
    -0.59
     '
    -0.59
     (
    -0.59
    Portale
    -0.54
     [
    -0.52
     $
    -0.51
     InputDecoration
    -0.49
    VideoCapture
    -0.49
    POSITIVE LOGITS
     purpoſe
    0.80
     Conſ
    0.77
     ſch
    0.77
     Theſe
    0.77
     Anſ
    0.75
     Reſ
    0.74
     Diſ
    0.73
     Monfieur
    0.73
     ſche
    0.69
     ſtate
    0.67
    Activations Density 10.115%

    No Known Activations