© 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. 11528
    Prev
    Next
    INDEX
    Explanations

    plus signs followed by digits and the words 'tele', or 'tele' variants

    oai_token-act-pair · gemini-2.0-flash

    programming-related terms or code snippets

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

    links and times

    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
    +:+
    -0.94
     bezeichneter
    -0.79
    ineno
    -0.78
    AsUp
    -0.77
    Бахар
    -0.75
     propOrder
    -0.75
     Paglinawan
    -0.75
    fjspx
    -0.72
     getItemCount
    -0.72
    τια
    -0.69
    POSITIVE LOGITS
    ReusableCell
    0.43
     travaillons
    0.41
     slä
    0.39
    itinéraire
    0.36
    InputTagHelper
    0.35
    WebDriver
    0.35
     Waar
    0.35
     venuto
    0.34
    addLast
    0.34
    odzi
    0.34
    Activations Density 0.896%

    No Known Activations