© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8209
    Prev
    Next
    INDEX
    Explanations

    numbers including decimal places and commas

    oai_token-act-pair · gemini-2.0-flash

    Scientific and statistical numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    TagMode
    -0.71
    SourceChecksum
    -0.65
    +:+
    -0.57
    <!--[
    -0.54
    tonode
    -0.52
    UseVisualStyle
    -0.52
    __(/*!
    -0.49
    olera
    -0.49
     CURLOPT
    -0.46
    RuleContext
    -0.45
    POSITIVE LOGITS
    клопе
    0.71
    Personendaten
    0.67
    новниш
    0.55
    Erreferentziak
    0.55
    lgari
    0.54
    essandro
    0.52
     kaarangay
    0.51
    ConverterFactory
    0.50
    verwijspagina
    0.50
    Gambas
    0.50
    Activations Density 2.251%

    No Known Activations