© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6483
    Prev
    Next
    INDEX
    Explanations

    the word "bank" and related terms like "account."

    oai_token-act-pair · gemini-2.0-flash

    bank

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     null
    -0.50
    mapStateToProps
    -0.47
    StateToProps
    -0.46
    varande
    -0.44
     trúc
    -0.44
    ázaro
    -0.44
    folger
    -0.43
     بتاريخ
    -0.43
     ilma
    -0.43
     Cámara
    -0.42
    POSITIVE LOGITS
    ChildScrollView
    0.80
    NameInMap
    0.75
     CreateTagHelper
    0.73
    UserScript
    0.66
    endphp
    0.66
    +#+#
    0.66
     defaultstate
    0.64
    )++;
    0.64
     lenker
    0.62
    rungsseite
    0.62
    Activations Density 0.466%

    No Known Activations