© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5111
    Prev
    Next
    INDEX
    Explanations

    html markup and email headers

    oai_token-act-pair · gemini-2.0-flash

    Code or structured data

    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
     تضيفلها
    -1.07
     nakalista
    -1.05
     disambiguazione
    -1.00
    تقاوى
    -1.00
     للاسماء
    -0.99
    ########.
    -0.97
    featureID
    -0.88
    rrggbb
    -0.87
    webElementXpaths
    -0.84
    MessageOf
    -0.84
    POSITIVE LOGITS
     U
    0.49
     Mo
    0.47
     S
    0.47
     جمله
    0.45
     x
    0.44
     T
    0.44
     term
    0.44
     O
    0.44
    yttä
    0.43
     Ho
    0.43
    Activations Density 0.167%

    No Known Activations