© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11250
    Prev
    Next
    INDEX
    Explanations

    legal documents with citations, names and numbers

    oai_token-act-pair · gemini-2.0-flash

    legal cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    AndEndTag
    -0.81
    IsContent
    -0.78
     चीज़ों
    -0.74
    GraphicsUnit
    -0.71
    AddTagHelper
    -0.69
     cherchés
    -0.68
    WithFormat
    -0.65
    NOPQRST
    -0.65
     "..\..\
    -0.63
    fromnode
    -0.63
    POSITIVE LOGITS
    ituary
    0.46
     lang
    0.45
    SuppressLint
    0.40
     panas
    0.39
    glement
    0.39
    istos
    0.39
    }-(
    0.38
    Портал
    0.38
     Miracle
    0.37
     rayos
    0.37
    Activations Density 2.038%

    No Known Activations