© 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. 8876
    Prev
    Next
    INDEX
    Explanations

    words starting with "ox", "lex", "rox", "dex" or "kus"

    oai_token-act-pair · gemini-2.0-flash

    names of works or titles

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

    Lex

    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
     препратки
    -0.68
    NameInMap
    -0.67
    InputBorder
    -0.63
    Izvori
    -0.62
    TagMode
    -0.59
     BorderSide
    -0.57
     odkazy
    -0.52
    dafx
    -0.50
    ftagPool
    -0.48
    /******/
    -0.48
    POSITIVE LOGITS
    Filmographie
    0.65
     Italijanski
    0.57
    Vidite
    0.56
    __':
    0.53
    Demografia
    0.50
     AssemblyTitle
    0.50
     پایان
    0.49
    elter
    0.48
    $^{-
    0.48
    LogFactory
    0.47
    Activations Density 0.694%

    No Known Activations