© 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. 15464
    Prev
    Next
    INDEX
    Explanations

    technical writing (including: measurements, experimental results, research)

    oai_token-act-pair · gemini-2.0-flash

    Research and technical writing

    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
     للمعارف
    -0.48
    wapV
    -0.45
    iska
    -0.45
     unclean
    -0.45
    WithFormat
    -0.45
    zał
    -0.44
     الرياضيه
    -0.44
    BeginContext
    -0.44
     esternos
    -0.44
     بما
    -0.43
    POSITIVE LOGITS
    клопе
    0.74
     CreateTagHelper
    0.73
     RIPRODUZIONE
    0.61
    didSet
    0.61
    tikzpicture
    0.60
    NUMX
    0.60
    ftagPool
    0.58
    styleType
    0.55
    VERTISEMENT
    0.54
    UserScript
    0.54
    Activations Density 43.332%

    No Known Activations