© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3663
    Prev
    Next
    INDEX
    Explanations

    legal language related to agreements, law, and procedures

    oai_token-act-pair · gemini-2.0-flash

    Expectation and intention

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     pyplot
    -0.54
     ver
    -0.38
    iso
    -0.37
    βο
    -0.37
    bol
    -0.36
    conda
    -0.36
    ben
    -0.36
    浮か
    -0.35
    lampa
    -0.35
     vis
    -0.35
    POSITIVE LOGITS
     supposed
    1.98
    supposed
    1.77
     suppose
    1.63
     suppos
    1.26
     supposes
    1.23
     meant
    1.11
    meant
    1.03
     intended
    1.01
     Intended
    1.00
     المعيارى
    0.98
    Activations Density 1.242%

    No Known Activations