© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12325
    Prev
    Next
    INDEX
    Explanations

    words and phrases that relate to groups, organizations, teams, clubs, conventions, committees, fanbases, memberships, voters, and associations

    oai_token-act-pair · gemini-2.0-flash

    clubs and conventions

    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
     memberships
    -0.72
     donors
    -0.67
    yntaxException
    -0.64
     Volunteers
    -0.63
     volunteers
    -0.62
     tartalomajánló
    -0.60
     Meetup
    -0.59
     Donations
    -0.59
     Charities
    -0.58
     treasurer
    -0.58
    POSITIVE LOGITS
    thâu
    0.62
     AttributeSet
    0.55
     dignidad
    0.50
    IndentedString
    0.45
    readValue
    0.44
    UrlEncoded
    0.44
     nacht
    0.44
    freopen
    0.43
    eachtet
    0.43
    RequiresApi
    0.43
    Activations Density 9.204%

    No Known Activations