© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15158
    Prev
    Next
    INDEX
    Explanations

    forms of the word "bound" and related legal/official concepts

    oai_token-act-pair · gemini-2.0-flash

    bound

    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
    Not in Any Lists

    No Comments

    Negative Logits
     calendriers
    -0.82
     Bourgoin
    -0.79
     bien
    -0.75
     mej
    -0.75
        
    -0.73
    pexpr
    -0.73
     forward
    -0.73
     para
    -0.72
     af
    -0.72
     *
    -0.70
    POSITIVE LOGITS
     Efq
    1.40
     Jefus
    1.35
     Reſ
    1.34
     Diſ
    1.34
     photolibrary
    1.30
     ſever
    1.29
    ")));
    1.29
     itſelf
    1.28
     pleaſure
    1.27
     myſelf
    1.27
    Activations Density 2.713%

    No Known Activations