© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4042
    Prev
    Next
    INDEX
    Explanations

    discussions of race, ethnicity, and representation, including political parties and demographic analysis

    oai_token-act-pair · gemini-2.0-flash

    Ethnic/racial groups

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    QMetaType
    -0.73
     <=",
    -0.62
     الحره
    -0.59
     يتيمه
    -0.58
     BoxFit
    -0.56
     חיצוניים
    -0.53
    orari
    -0.52
    ----</
    -0.51
     Norges
    -0.50
    verifyException
    -0.50
    POSITIVE LOGITS
     Lat
    0.62
    styleUrls
    0.58
    calipsis
    0.57
     lat
    0.56
    Lat
    0.56
     AssemblyCulture
    0.54
    tvguidetime
    0.52
    hists
    0.52
    lat
    0.51
    Tikang
    0.49
    Activations Density 4.804%

    No Known Activations