© 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. 7010
    Prev
    Next
    INDEX
    Explanations

    words describing roles or jobs within a company specifically "customer relations" and "public relations"

    oai_token-act-pair · gemini-2.0-flash

    administrative

    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
    TestBed
    -0.51
    MessageTagHelper
    -0.51
     Silverman
    -0.49
     resultCode
    -0.45
    theros
    -0.43
    チュ
    -0.43
    følgelig
    -0.43
    multirow
    -0.42
     Hild
    -0.42
    طني
    -0.42
    POSITIVE LOGITS
     administrative
    1.51
     administration
    1.29
     Administrative
    1.28
    administrative
    1.25
     admin
    1.23
    Administrative
    1.16
     administrativa
    1.15
     administr
    1.12
     Administration
    1.09
    administration
    1.08
    Activations Density 1.023%

    No Known Activations