© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11720
    Prev
    Next
    INDEX
    Explanations

    references to the Indian Institute of Management Ahmedabad

    oai_token-act-pair · gemini-2.0-flash

    technical terms or programming-related words

    np_token-act-pair-logits · gpt-4o-mini

    academic papers/institutions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     MEDICAL
    -0.56
     medical
    -0.56
     NUKAT
    -0.55
     الحره
    -0.54
     '\\;'
    -0.53
     Theſe
    -0.53
    ViewFeatures
    -0.52
    帖最后由
    -0.52
     تضيفلها
    -0.51
     Medical
    -0.51
    POSITIVE LOGITS
    saraba
    0.59
    LLocation
    0.52
     onOptions
    0.51
    celotti
    0.51
    styleType
    0.50
    StandardCharsets
    0.49
     دهند
    0.49
    íně
    0.48
    ParallelGroup
    0.48
    ViewChild
    0.47
    Activations Density 0.458%

    No Known Activations