© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16358
    Prev
    Next
    INDEX
    Explanations

    academic titles and governmental bodies and positions

    oai_token-act-pair · gemini-2.0-flash

    Names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    Források
    -0.49
     consultato
    -0.48
     Cusco
    -0.46
    Jegyzetek
    -0.46
     Vikipedi
    -0.45
     Wray
    -0.44
    ]=='
    -0.43
    ]=="
    -0.42
    ′
    -0.42
    原始内容存档于
    -0.42
    POSITIVE LOGITS
    TagHelper
    0.74
     ویکی‌پدی
    0.71
    AddTagHelper
    0.70
    RegressionTest
    0.70
    DNEY
    0.67
    UnusedPrivate
    0.65
     CURIAM
    0.63
    braio
    0.63
    DispatchToProps
    0.60
    ensaft
    0.59
    Activations Density 1.366%

    No Known Activations