© 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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5078
    Prev
    Next
    INDEX
    Explanations

    descriptions of clothing or accessories combined with possessive adjectives

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to programming or software development

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

    costumes and fabrics

    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
    with
    -0.47
    ([...
    -0.42
     with
    -0.42
    per
    -0.41
    дыду
    -0.40
    _{
    -0.40
     prendas
    -0.39
    v
    -0.38
    重
    -0.38
    Show
    -0.37
    POSITIVE LOGITS
    tagHelperRunner
    0.99
    StoryboardSegue
    0.98
    SourceChecksum
    0.92
    InjectAttribute
    0.90
    MLLoader
    0.90
     AssemblyProduct
    0.89
     препратки
    0.86
    RenderAtEndOf
    0.84
     BrowserModule
    0.79
    stateProvider
    0.78
    Activations Density 1.522%

    No Known Activations