© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9937
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to membership or being a part of something

    oai_token-act-pair · gemini-2.0-flash

    list membership/description

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    UVWXYZ
    -0.78
     nonatomic
    -0.66
     propOrder
    -0.65
     Pasteur
    -0.63
    requestCode
    -0.63
    PyExc
    -0.63
    SuppressLint
    -0.60
    thenia
    -0.60
     palmar
    -0.60
    thâu
    -0.59
    POSITIVE LOGITS
     member
    1.46
     members
    1.42
     Members
    1.28
    Members
    1.26
    member
    1.24
     Member
    1.23
     membership
    1.23
    members
    1.20
    Member
    1.16
     MEMBERS
    1.09
    Activations Density 1.140%

    No Known Activations