© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12042
    Prev
    Next
    INDEX
    Explanations

    technical features and descriptive concepts in various fields

    oai_token-act-pair · gemini-2.0-flash

    scientific writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    parsedMessage
    -0.80
    principalTable
    -0.80
    featureID
    -0.75
     mergeFrom
    -0.73
    تقاوى
    -0.73
    GEBURTSDATUM
    -0.72
    ThroughAttribute
    -0.72
    writeFieldEnd
    -0.72
    ьаж
    -0.71
     سكانية
    -0.71
    POSITIVE LOGITS
     rospy
    0.53
    ccione
    0.48
    ocuk
    0.46
    aneous
    0.43
     становника
    0.43
     suspension
    0.43
     attracting
    0.43
    httphttps
    0.42
    acle
    0.41
     كومونز
    0.41
    Activations Density 0.610%

    No Known Activations