© 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. 13505
    Prev
    Next
    INDEX
    Explanations

    various components of legal arguments, procedures, judgments, medical terms, or scientific background information.

    oai_token-act-pair · gemini-2.0-flash

    Technical/legal texts

    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
    ItemBackground
    -0.81
     متعلقه
    -0.79
     EconPapers
    -0.78
    TintMode
    -0.78
     crdi
    -0.75
     pleaſure
    -0.73
    parsedMessage
    -0.72
    /**
    -0.71
     Efq
    -0.71
    UnitTesting
    -0.71
    POSITIVE LOGITS
     CURIAM
    0.61
     Amanda
    0.53
     am
    0.53
    <eos>
    0.50
    OCCURRED
    0.48
     τ
    0.47
     Sch
    0.46
     CA
    0.45
     Schra
    0.45
    ToMany
    0.45
    Activations Density 5.294%

    No Known Activations