© 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. 14895
    Prev
    Next
    INDEX
    Explanations

    any numerical values or code elements

    oai_token-act-pair · gemini-2.0-flash

    programming or coding-related terminology

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

    say "0"

    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
    nthesis
    -0.52
    oso
    -0.47
    ̣
    -0.47
    []
    -0.46
    Arne
    -0.45
    ΗΣ
    -0.43
     BR
    -0.42
     Dy
    -0.41
     braccio
    -0.41
     मदद
    -0.41
    POSITIVE LOGITS
    ItemBackground
    0.71
    parsedMessage
    0.71
    AndEndTag
    0.70
    aarrggbb
    0.69
     GenerationType
    0.69
     gainera
    0.69
    ContentAsync
    0.67
     Савезне
    0.67
    enumi
    0.67
    EDEFAULT
    0.67
    Activations Density 8.566%

    No Known Activations