© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10908
    Prev
    Next
    INDEX
    Explanations

    references to the phrase "third party", as well as the related "either party"

    oai_token-act-pair · gemini-2.0-flash

    third party

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     party
    -2.34
     Party
    -2.28
     PARTY
    -2.22
    Party
    -2.22
     parties
    -2.22
    party
    -2.16
    PARTY
    -2.14
     Parties
    -2.11
    parties
    -2.08
    Parties
    -1.97
    POSITIVE LOGITS
    angle
    0.39
    PO
    0.36
     \
    0.36
     össze
    0.36
     =
    0.35
     lente
    0.35
    frac
    0.34
    sqrt
    0.34
    GET
    0.33
     po
    0.33
    Activations Density 1.575%

    No Known Activations