© 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. 9146
    Prev
    Next
    INDEX
    Explanations

    text that is part of a comment about items dropping in a game

    oai_token-act-pair · gemini-2.0-flash

    technical terms or functions related to programming

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

    '

    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
     characters
    -0.54
    oneofs
    -0.54
     Characters
    -0.53
    Spécification
    -0.51
     personnages
    -0.51
     مواليد
    -0.49
     汉
    -0.49
    walde
    -0.49
     character
    -0.49
     phí
    -0.49
    POSITIVE LOGITS
     AssemblyTitle
    0.76
    出版年
    0.71
    Referanser
    0.60
    createComponent
    0.56
     JOptionPane
    0.54
     مشين
    0.52
     препратки
    0.52
     springfox
    0.51
    ResumeLayout
    0.51
    __(/*!
    0.51
    Activations Density 0.473%

    No Known Activations