© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4588
    Prev
    Next
    INDEX
    Explanations

    words related to commerce and transactions in a local area

    oai_token-act-pair · gemini-2.0-flash

    store names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     noqa
    -0.58
     Tasse
    -0.50
     ministerial
    -0.48
     przyzna
    -0.44
    ؤ
    -0.42
    UnknownFields
    -0.42
     cytotoxicity
    -0.42
     conductance
    -0.41
    InputBorder
    -0.40
     cauza
    -0.40
    POSITIVE LOGITS
     Target
    0.83
     Home
    0.75
     يتيمه
    0.73
     Kohl
    0.72
     Lowe
    0.71
     Wal
    0.69
    Target
    0.69
     Amazon
    0.68
    ThroughAttribute
    0.66
     Targets
    0.66
    Activations Density 1.826%

    No Known Activations