© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5573
    Prev
    Next
    INDEX
    Explanations

    references to social issues and living conditions, including poverty, housing, employment, and inequality.

    oai_token-act-pair · gemini-2.0-flash

    words related to social issues and housing

    np_token-act-pair-logits · gpt-4o-mini

    live

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    eddah
    -0.57
    centralwidget
    -0.54
    dafx
    -0.54
    ÍN
    -0.53
    ESTAMP
    -0.52
    <bos>
    -0.51
    cussions
    -0.51
     their
    -0.51
     technical
    -0.50
    makeConstraints
    -0.50
    POSITIVE LOGITS
    __*/
    0.75
     bouteilles
    0.60
     ujednoznacz
    0.59
     متعلقه
    0.58
     preuves
    0.56
     lèvres
    0.55
    󠁿
    0.55
     Egli
    0.54
     braccia
    0.54
     FetchType
    0.54
    Activations Density 5.154%

    No Known Activations