© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11401
    Prev
    Next
    INDEX
    Explanations

    fragments of words

    oai_token-act-pair · gemini-2.0-flash

    science/medicine

    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
    v
    -0.43
     hini
    -0.42
    opsida
    -0.42
    launcher
    -0.41
    <0x93>
    -0.41
    ↵↵
    -0.41
    gen
    -0.40
    {
    -0.39
    \\
    -0.39
    chá
    -0.38
    POSITIVE LOGITS
     '\\;'
    0.81
    GEBURTS
    0.73
    ließlich
    0.70
    
    0.69
    posedge
    0.68
    SequentialGroup
    0.68
     propOrder
    0.68
    ConstraintMaker
    0.68
     intptr
    0.67
    JNIEnv
    0.66
    Activations Density 5.517%

    No Known Activations