© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13233
    Prev
    Next
    INDEX
    Explanations

    the word "custom" and words relating to the manufacturing or branding of products.

    oai_token-act-pair · gemini-2.0-flash

    custom-made products

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

    custom

    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
    IndentedString
    -0.54
     mesmas
    -0.52
    zbęd
    -0.52
    достатки
    -0.52
     againſt
    -0.50
     betroffen
    -0.50
     afectadas
    -0.50
     originales
    -0.49
    ReferenceEquals
    -0.49
     tartalomajánló
    -0.49
    POSITIVE LOGITS
     архивлан
    0.61
    webElementXpaths
    0.54
    scalatest
    0.50
    FieldNumber
    0.50
     AssemblyTitle
    0.49
     SearchView
    0.48
     FormData
    0.48
    CardHeader
    0.48
     esternos
    0.48
     filed
    0.47
    Activations Density 3.828%

    No Known Activations