© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10510
    Prev
    Next
    INDEX
    Explanations

    sentences referencing the Western Sahara and the United Nations

    oai_token-act-pair · gemini-2.0-flash

    international relations/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
     виправивши
    -0.54
    cles
    -0.47
    CppMethod
    -0.47
    mulo
    -0.46
     Be
    -0.46
     Mul
    -0.45
    कल
    -0.45
    ̉
    -0.44
     MUL
    -0.43
    Be
    -0.42
    POSITIVE LOGITS
    ^(@)
    0.70
    MLLoader
    0.66
     initComponents
    0.65
    __':
    0.63
    RegistryLite
    0.63
    )')
    0.61
    principalColumn
    0.60
    CDCl
    0.60
    YOND
    0.59
    PointerException
    0.59
    Activations Density 2.140%

    No Known Activations