© 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. 14858
    Prev
    Next
    INDEX
    Explanations

    legal and financial text, including court decisions, measurements, filing codes, and tax codes.

    oai_token-act-pair · gemini-2.0-flash

    Legal/technical document

    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
    </blockquote>
    -0.94
    μεν
    -0.57
    keit
    -0.52
    iert
    -0.50
     nonatomic
    -0.49
     embargo
    -0.49
    MoveNext
    -0.49
    miert
    -0.49
     master
    -0.48
    ResponseWriter
    -0.48
    POSITIVE LOGITS
     betweenstory
    0.69
    LookAnd
    0.63
    windowFixed
    0.63
    FunctionFlags
    0.60
    มาะ
    0.60
    ✨:
    0.58
    yntaxException
    0.57
    errHandler
    0.56
    contentPane
    0.56
    SequentialGroup
    0.54
    Activations Density 2.544%

    No Known Activations