© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10170
    Prev
    Next
    INDEX
    Explanations

    words pertaining to licensing, telecommunications, and electronic functions

    oai_token-act-pair · gemini-2.0-flash

    telecommunications and licenses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    expandindo
    -1.25
     виправивши
    -1.20
     AssemblyCulture
    -1.13
    <bos>
    -1.11
     ModelExpression
    -1.08
    NameInMap
    -1.06
     AssemblyTitle
    -1.03
     snippetHide
    -0.99
     beginnetje
    -0.99
    ValueStyle
    -0.98
    POSITIVE LOGITS
     Wilk
    0.56
     Karla
    0.55
     a
    0.52
     отношению
    0.50
    ame
    0.49
     L
    0.48
    TER
    0.48
    FormComponent
    0.47
     McL
    0.47
     F
    0.47
    Activations Density 2.137%

    No Known Activations