© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13486
    Prev
    Next
    INDEX
    Explanations

    the word "infrastructure" and words that commonly appear near it

    oai_token-act-pair · gemini-2.0-flash

    infrastructure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    era
    -0.82
    ora
    -0.68
    HandlerContext
    -0.58
    ă
    -0.57
    aran
    -0.57
    ########.
    -0.57
    ERA
    -0.55
    expandindo
    -0.53
    enment
    -0.53
    ORA
    -0.50
    POSITIVE LOGITS
     Roskov
    0.65
    ſhip
    0.63
    CLING
    0.60
    endphp
    0.58
     hữu
    0.58
     estekak
    0.58
    viewDidLoad
    0.57
    bustion
    0.57
     {},
    0.57
    /*
    0.56
    Activations Density 1.665%

    No Known Activations