© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10804
    Prev
    Next
    INDEX
    Explanations

    mentions of militant groups and locations in the Congo

    oai_token-act-pair · gemini-2.0-flash

    Conflict in Africa

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     समीक्षाओं
    -0.67
     للمعارف
    -0.60
    MessageState
    -0.60
    ValueStyle
    -0.59
    iastical
    -0.59
    oredCriteria
    -0.57
     himo
    -0.55
    CppMethod
    -0.55
    IndentedString
    -0.53
    marvin
    -0.51
    POSITIVE LOGITS
     ModelExpression
    0.57
    benar
    0.48
     néglig
    0.47
    akse
    0.47
     κύ
    0.47
     FetchType
    0.46
     signé
    0.46
    honneur
    0.45
    PathVariable
    0.45
    ="@+
    0.45
    Activations Density 0.763%

    No Known Activations