© 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. 10214
    Prev
    Next
    INDEX
    Explanations

    geopolitical accusations, particularly those involving the US, Russia or other countries

    oai_token-act-pair · gemini-2.0-flash

    Political/legal discussions

    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
    "]();
    -0.57
    Tembelea
    -0.56
    uxxxx
    -0.53
    protoimpl
    -0.52
    ொ
    -0.52
     Territories
    -0.50
    Personendaten
    -0.50
    ofire
    -0.49
    principalTable
    -0.48
    فته
    -0.48
    POSITIVE LOGITS
    ContentAlignment
    0.69
    MigrationBuilder
    0.49
     contemporaine
    0.48
    Diweddarwch
    0.46
     chrétienne
    0.46
    ButtonStyle
    0.45
     chrétien
    0.45
     EnglishChoose
    0.44
    Хьажоргаш
    0.44
    dinga
    0.43
    Activations Density 2.003%

    No Known Activations