© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7085
    Prev
    Next
    INDEX
    Explanations

    language and terminology used in legal documents involving statutes, agreements, and medical trials

    oai_token-act-pair · gemini-2.0-flash

    "or" in other languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    ak
    -0.53
    No
    -0.47
     Reverso
    -0.44
    tams
    -0.43
    вест
    -0.43
    makeText
    -0.42
     No
    -0.42
    ysen
    -0.41
     الرياضيه
    -0.41
    fp
    -0.40
    POSITIVE LOGITS
    Или
    0.79
     or
    0.78
    ########.
    0.74
    ArrowToggle
    0.74
     или
    0.70
    Viited
    0.66
     ή
    0.64
     또는
    0.64
    หรือ
    0.63
    或
    0.63
    Activations Density 1.890%

    No Known Activations