© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1866
    Prev
    Next
    INDEX
    Explanations

    words containing "bri" or "bor"

    oai_token-act-pair · gemini-2.0-flash

    "to be honest"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ftagPool
    -0.84
     للاسماء
    -0.80
    ThroughAttribute
    -0.79
    kháu
    -0.77
    SequentialGroup
    -0.73
     Infórmanos
    -0.69
    */;
    -0.66
    ScopeManager
    -0.66
    .*")]
    -0.65
    RegressionTest
    -0.65
    POSITIVE LOGITS
     Roll
    0.46
    euler
    0.43
     состоя
    0.42
    が開
    0.41
    Часть
    0.41
    ått
    0.41
     critical
    0.39
    tellation
    0.39
    rollers
    0.38
     Bo
    0.38
    Activations Density 0.712%

    No Known Activations