© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15078
    Prev
    Next
    INDEX
    Explanations

    mentions of governing bodies, formal documents, and the actions of the powerful.

    oai_token-act-pair · gemini-2.0-flash

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    脚注の使い方
    -0.61
    __":
    -0.60
    __':
    -0.59
    stdc
    -0.59
     ostavi
    -0.56
    gnancy
    -0.56
     eventdata
    -0.55
     thereon
    -0.55
     تانيه
    -0.54
     nisso
    -0.54
    POSITIVE LOGITS
     Himo
    0.64
     himo
    0.57
    oa̍t
    0.57
     frigor
    0.50
    windowFixed
    0.47
     ویکی‌پدی
    0.47
     porad
    0.46
    pides
    0.46
    umsi
    0.45
     esternos
    0.45
    Activations Density 21.605%

    No Known Activations