© 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. 9124
    Prev
    Next
    INDEX
    Explanations

    commas and words related to scientific academic papers.

    oai_token-act-pair · gemini-2.0-flash

    commas

    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
     utafitiHapana
    -0.83
    contentLoaded
    -0.82
    ंदीखरीदारी
    -0.69
    Rüyada
    -0.69
     समीक्षाओं
    -0.67
    ItemBackground
    -0.64
    __":
    -0.64
    ValueStyle
    -0.63
     Wikimedijinoj
    -0.62
     brim
    -0.61
    POSITIVE LOGITS
     ориги
    0.46
    lichter
    0.45
     habet
    0.45
     استر
    0.44
     anzub
    0.40
    permitAll
    0.40
     recargable
    0.40
     enged
    0.39
     glisser
    0.39
     craindre
    0.38
    Activations Density 0.480%

    No Known Activations