© 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. 2877
    Prev
    Next
    INDEX
    Explanations

    code, including inequalities, pointers, and hex constants

    oai_token-act-pair · gemini-2.0-flash

    programming symbols and syntax elements

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

    code

    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
     Gub
    -0.45
    apé
    -0.41
     verrez
    -0.40
    而不是
    -0.40
    HttpPost
    -0.40
     rằng
    -0.39
    enic
    -0.39
     tud
    -0.38
    ＝
    -0.38
    리는
    -0.38
    POSITIVE LOGITS
    VersionUID
    0.72
    CppMethod
    0.68
    fcntl
    0.64
    UVWXYZ
    0.62
    rizona
    0.62
     surla
    0.62
    +:+
    0.62
     invokingState
    0.61
    uxxxx
    0.61
     disambiguazione
    0.60
    Activations Density 3.990%

    No Known Activations