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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 41
    Prev
    Next
    INDEX
    Explanations

    words related to political processes and Brazilian political parties

    oai_token-act-pair · gemini-2.0-flash

    Brazilian politics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ########.
    -0.71
     insuffisamment
    -0.59
    OGND
    -0.54
     surla
    -0.53
     ProtoMessage
    -0.50
     خارجية
    -0.49
    MigrationBuilder
    -0.48
    Ъ
    -0.47
    GEBURTSDATUM
    -0.47
    balleur
    -0.46
    POSITIVE LOGITS
    TagMode
    0.69
    writeHead
    0.52
    ToScroll
    0.50
     Fif
    0.50
     Ow
    0.47
    crollView
    0.47
     geral
    0.46
     AppCompat
    0.46
    General
    0.46
     sés
    0.46
    Activations Density 2.165%

    No Known Activations