© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6578
    Prev
    Next
    INDEX
    Explanations

    the word "facility" or a variation of it.

    oai_token-act-pair · gemini-2.0-flash

    facility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     facility
    -2.75
     facilities
    -2.70
     Facility
    -2.58
    Facility
    -2.48
     Facilities
    -2.48
    facility
    -2.47
    facilities
    -2.38
    Facilities
    -2.28
     FACILITIES
    -2.23
     FACILITY
    -2.23
    POSITIVE LOGITS
     CreateTagHelper
    0.56
    InjectAttribute
    0.55
    CppCodeGen
    0.54
    bootstrapcdn
    0.52
    jspx
    0.52
     disambiguazione
    0.52
    IVEREF
    0.51
    IndentedString
    0.51
    UrlEncoded
    0.51
     resourceCulture
    0.51
    Activations Density 0.300%

    No Known Activations