© 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
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12592
    Prev
    Next
    INDEX
    Explanations

    email addresses and postal addresses

    oai_token-act-pair · gemini-2.0-flash

    email addresses or URL formats

    np_token-act-pair-logits · gpt-4o-mini

    @

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    writeFieldEnd
    -0.63
    AsUp
    -0.61
    öße
    -0.60
    AndEndTag
    -0.58
     fédé
    -0.56
    ädie
    -0.54
    randi
    -0.54
     дописавши
    -0.54
     sauvages
    -0.53
    RTHOOK
    -0.53
    POSITIVE LOGITS
    atecas
    0.45
    ControllerAdvice
    0.42
    Istorija
    0.42
    include
    0.41
     AutoMapper
    0.41
     ostavi
    0.41
    SerializedSize
    0.41
    意外と
    0.40
     Viper
    0.40
     excepción
    0.40
    Activations Density 0.365%

    No Known Activations