© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 7719
    Prev
    Next
    INDEX
    Explanations

    code and data structures, especially in networking and embedded systems contexts, with a preference for a series of digits where all are the same but with 1 exception

    oai_token-act-pair · gemini-2.0-flash

    numeric values and specific variable types

    np_token-act-pair-logits · gpt-4o-mini
    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
     Meksiku
    -0.78
    сылкі
    -0.76
    +#+#
    -0.74
    RegressionTest
    -0.72
    WebVitals
    -0.72
    }{*}{
    -0.71
     chi̍t
    -0.69
     Wikimedijinoj
    -0.68
    DataAnnotations
    -0.66
    IsContent
    -0.64
    POSITIVE LOGITS
    2
    0.69
    copio
    0.46
    ২
    0.44
     novio
    0.43
    十二
    0.42
    dienst
    0.42
     udara
    0.40
    ிற
    0.40
    ط
    0.39
    زم
    0.39
    Activations Density 0.893%

    No Known Activations