© 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. 12921
    Prev
    Next
    INDEX
    Explanations

    the names of Tanzanian endangered animals, people harming animals, and the phrase "red colobus."

    oai_token-act-pair · gemini-2.0-flash

    primates

    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
     poverty
    -0.51
    󠁣
    -0.48
    Poverty
    -0.44
     Poverty
    -0.43
     poor
    -0.43
    poverty
    -0.42
     impoverished
    -0.42
     loan
    -0.41
     powerless
    -0.41
    Poor
    -0.41
    POSITIVE LOGITS
    ThroughAttribute
    0.76
    Personendaten
    0.76
    انيف
    0.66
     مرئيه
    0.64
    msgTypes
    0.63
    oredCriteria
    0.63
    AccessorTable
    0.63
     Paglinawan
    0.62
     للمعارف
    0.60
     combineReducers
    0.59
    Activations Density 1.569%

    No Known Activations