© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11561
    Prev
    Next
    INDEX
    Explanations

    language about advocacy for children and education

    oai_token-act-pair · gemini-2.0-flash

    human rights and policy

    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
     kasarigan
    -0.80
    migrationBuilder
    -0.74
    Hochspringen
    -0.74
    reportWebVitals
    -0.73
    intios
    -0.71
    esez
    -0.70
    PreferredItem
    -0.69
     createState
    -0.68
    ButtonStyle
    -0.68
    interopRequire
    -0.67
    POSITIVE LOGITS
    彼女は
    0.40
     रेटिंग
    0.36
     insuffisamment
    0.35
     continuant
    0.35
    isible
    0.35
    don
    0.35
     AppBundle
    0.35
    vč
    0.34
    ängerin
    0.34
    ạch
    0.34
    Activations Density 2.357%

    No Known Activations