© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13525
    Prev
    Next
    INDEX
    Explanations

    mentions of "parties" in a legal context, especially where agreements are being considered.

    oai_token-act-pair · gemini-2.0-flash

    parties

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ISATION
    -0.54
    دانشنامهٔ
    -0.54
     organising
    -0.52
     organiser
    -0.52
    utin
    -0.51
    sellor
    -0.51
     Ay
    -0.51
    Anal
    -0.50
    (‘
    -0.50
    '].'
    -0.50
    POSITIVE LOGITS
     CreateTagHelper
    0.79
     autorytatywna
    0.71
    çamento
    0.69
     calendriers
    0.67
    pointments
    0.66
     horaire
    0.66
     mukana
    0.65
     veci
    0.65
    sumowanie
    0.64
    pointment
    0.63
    Activations Density 1.242%

    No Known Activations