© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13233
    Prev
    Next
    INDEX
    Explanations

    words and short phrases related to business or client relationships.

    oai_token-act-pair · gemini-2.0-flash

    clients/customer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     client
    -1.16
     Clients
    -1.13
     clients
    -1.09
     Client
    -1.09
    Client
    -1.07
    client
    -1.05
     clientes
    -1.03
     customer
    -0.99
     CLIENT
    -0.94
    Clients
    -0.93
    POSITIVE LOGITS
    CloseOperation
    0.82
    AddTagHelper
    0.76
     estekak
    0.71
    rouvez
    0.70
    лтемелер
    0.69
     }}"></
    0.68
    afficheront
    0.66
    nologue
    0.66
    Predecesor
    0.66
    MessageOf
    0.64
    Activations Density 22.027%

    No Known Activations