© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6076
    Prev
    Next
    INDEX
    Explanations

    URLs and related terms (e.g. website, https:, .com)

    oai_token-act-pair · gemini-2.0-flash

    links to data sources

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

    URLs and web addresses

    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
     http
    -1.20
     https
    -1.20
    https
    -1.13
    http
    -1.10
    ttps
    -0.93
     www
    -0.76
    setVerticalGroup
    -0.74
     bezeichneter
    -0.73
    parsedMessage
    -0.72
     Audiodateien
    -0.71
    POSITIVE LOGITS
     bit
    0.83
    BIT
    0.55
    bit
    0.55
     tiny
    0.54
    mises
    0.53
     Dot
    0.51
     bits
    0.51
     org
    0.50
     Bit
    0.50
    jusi
    0.50
    Activations Density 0.984%

    No Known Activations