Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 16-GEMMASCOPE-TRANSCODER-16K
    4. 1153
    Prev
    Next
    INDEX
    Explanations

    words related to social issues, community, and political action

    oai_token-act-pair · gemini-2.0-flash

    global societal issues

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.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
     inwoners
    -0.52
    Géographie
    -0.52
     Italijani
    -0.51
    Handlung
    -0.51
     ब्रेकडाउन
    -0.49
    Portail
    -0.49
    öglichkeiten
    -0.49
    allowNull
    -0.49
    phan
    -0.48
     Infórmanos
    -0.47
    POSITIVE LOGITS
     VIAF
    0.55
    idać
    0.52
    ParallelGroup
    0.52
    adpleegd
    0.51
     décédé
    0.50
     supérieurs
    0.50
     limitée
    0.50
    +:+
    0.49
    DockStyle
    0.49
    исленность
    0.48
    Activations Density 2.630%

    No Known Activations