© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13605
    Prev
    Next
    INDEX
    Explanations

    words related to binding agreements and promises to comply, or the opposite words denying or breaking commitments.

    oai_token-act-pair · gemini-2.0-flash

    restrictions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    adpleegd
    -0.73
    EndContext
    -0.72
     beginnetje
    -0.69
    IntoConstraints
    -0.66
    :✨
    -0.66
    DebuggerNonUser
    -0.64
    IUrlHelper
    -0.64
    OrNil
    -0.63
    hyrchwyd
    -0.58
    كويكب
    -0.57
    POSITIVE LOGITS
    readystatechange
    0.52
     manqué
    0.51
     vache
    0.49
     réunis
    0.49
    ートル
    0.48
     panggilan
    0.47
     maîtres
    0.45
     först
    0.44
     tarde
    0.43
    ambilan
    0.43
    Activations Density 21.397%

    No Known Activations