© 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. 5374
    Prev
    Next
    INDEX
    Explanations

    terms used in legal and business contexts, with a focus on representation and agreement

    oai_token-act-pair · gemini-2.0-flash

    represent

    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
    IsContent
    -0.84
     cauſe
    -0.66
     Majefty
    -0.64
     comigo
    -0.64
     ſtate
    -0.63
     flyknit
    -0.62
     myſelf
    -0.60
     élect
    -0.59
     purpoſe
    -0.58
     Theſe
    -0.58
    POSITIVE LOGITS
     ويكيميديا
    0.57
    detectChanges
    0.51
    rd
    0.48
     emp
    0.47
     disambiguazione
    0.46
    dtypes
    0.45
     kaynağından
    0.44
    ANTLR
    0.43
    RTEX
    0.43
    strSql
    0.42
    Activations Density 20.587%

    No Known Activations