© 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. 10830
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate argument or persuasion in a discussion, report, or document.

    oai_token-act-pair · gemini-2.0-flash

    the word "any"

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

    any

    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
    InputTagHelper
    -0.63
    ագրություններ
    -0.55
    lapsingToolbar
    -0.55
    glGen
    -0.55
    CloseOperation
    -0.54
     poveznice
    -0.52
    sistors
    -0.52
    WebServlet
    -0.51
    TypedDataSet
    -0.51
    InlineData
    -0.50
    POSITIVE LOGITS
     any
    2.80
    Any
    2.28
     Any
    2.27
    any
    2.25
     qualquer
    2.02
     ANY
    1.92
     cualquier
    1.91
    ANY
    1.84
    任何
    1.80
     qualsiasi
    1.79
    Activations Density 6.819%

    No Known Activations