© 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. 7894
    Prev
    Next
    INDEX
    Explanations

    code snippets and syntax, especially related to commands, functions, and tables

    oai_token-act-pair · gemini-2.0-flash

    technical command phrases

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

    Code and database operations

    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
    ysacchar
    -0.50
    tagHelper
    -0.44
     zoll
    -0.44
     CHtml
    -0.44
     written
    -0.44
    written
    -0.43
     Written
    -0.43
     hör
    -0.43
    mining
    -0.43
     Rocks
    -0.43
    POSITIVE LOGITS
    WithIOException
    0.62
     виправивши
    0.60
     Akismet
    0.58
     Vikipedi
    0.57
    脚注の使い方
    0.55
    Begriffsklä
    0.54
    principalTable
    0.54
     Audiodateien
    0.54
    '][$
    0.53
     createState
    0.53
    Activations Density 1.809%

    No Known Activations