© 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. 9634
    Prev
    Next
    INDEX
    Explanations

    a mix of political commentary, personal names, and possessives

    oai_token-act-pair · gemini-2.0-flash

    articles/blog posts

    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
    ItemBackground
    -0.59
     SearchView
    -0.58
    writeFieldEnd
    -0.57
     opérateur
    -0.56
     estimés
    -0.54
     onAnimation
    -0.54
    RotationOrder
    -0.53
    cam
    -0.52
    Hauptartikel
    -0.52
     nicio
    -0.51
    POSITIVE LOGITS
     useStyles
    0.55
    ('/:
    0.54
     useEffect
    0.52
     getPosition
    0.52
    CodedInputStream
    0.51
    ("/:
    0.51
     bỏng
    0.50
    Архівовано
    0.49
    interopRequire
    0.49
    zys
    0.48
    Activations Density 0.380%

    No Known Activations