© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9141
    Prev
    Next
    INDEX
    Explanations

    references to articles

    oai_token-act-pair · gemini-2.0-flash

    links to external references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     cherchés
    -0.67
     Meksiku
    -0.66
     ostavi
    -0.62
    webElementXpaths
    -0.60
    SBATCH
    -0.58
    carat
    -0.57
    Controllo
    -0.54
    ngdoc
    -0.54
    ThroughAttribute
    -0.54
     truk
    -0.53
    POSITIVE LOGITS
    ]--;
    0.45
    الدراسه
    0.45
    adə
    0.44
     Сайт
    0.43
     &___
    0.43
     unknownFields
    0.42
    setAdapter
    0.42
     esterni
    0.39
     Overland
    0.38
    itoriale
    0.38
    Activations Density 1.360%

    No Known Activations