© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10119
    Prev
    Next
    INDEX
    Explanations

    legal jargon related to intentionality, purpose and legal statutes

    oai_token-act-pair · gemini-2.0-flash

    purpose

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     purpose
    -2.86
     purposes
    -2.55
    purpose
    -2.38
     Purpose
    -2.36
    Purpose
    -2.36
     PURPOSE
    -2.16
    purposes
    -1.99
     Purposes
    -1.98
    PURPOSE
    -1.95
     purpoſe
    -1.76
    POSITIVE LOGITS
    DllImport
    0.59
    ViewChild
    0.47
    cencia
    0.47
     Oldest
    0.46
     Personalised
    0.45
    ότε
    0.44
    tron
    0.44
    NgModule
    0.43
    erialization
    0.43
     Elsewhere
    0.43
    Activations Density 10.624%

    No Known Activations