© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13804
    Prev
    Next
    INDEX
    Explanations

    references to online content, particularly videos and articles, and associated connector words or phrases

    oai_token-act-pair · gemini-2.0-flash

    programming keywords or functions

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

    technical references and sources

    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
     veda
    -0.40
    WinForms
    -0.39
     nors
    -0.35
    batik
    -0.35
    PostBack
    -0.35
    XXI
    -0.34
     asequ
    -0.34
     preocupes
    -0.33
    DialogComponent
    -0.33
    сил
    -0.33
    POSITIVE LOGITS
     initComponents
    0.98
    exitRule
    0.96
    ArgsConstructor
    0.89
     AssemblyProduct
    0.87
    PerformLayout
    0.85
    +#+#
    0.83
    MessageTagHelper
    0.83
     getItemId
    0.82
    Obrázky
    0.81
     مشين
    0.80
    Activations Density 1.566%

    No Known Activations