© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12335
    Prev
    Next
    INDEX
    Explanations

    references to laws, regulations, statutes, and legal terminology

    oai_token-act-pair · gemini-2.0-flash

    terms related to legal documents or code

    np_token-act-pair-logits · gpt-4o-mini

    US legal acts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    LookAnd
    -0.62
     Walkover
    -0.61
     '\\;'
    -0.59
     دیکھیے
    -0.57
    hadur
    -0.52
    struts
    -0.49
     *)__
    -0.49
    AsUp
    -0.49
     ✭✭
    -0.49
     Roskov
    -0.47
    POSITIVE LOGITS
    </thead>
    0.66
    yntaxException
    0.56
     réguli
    0.52
     المعيارى
    0.52
    (!__
    0.51
    gaben
    0.50
    DispatchToProps
    0.50
    glPopMatrix
    0.47
    pios
    0.47
     culturelles
    0.47
    Activations Density 1.314%

    No Known Activations