© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 2722
    Prev
    Next
    INDEX
    Explanations

    a jumble of different contexts including dates, familial relations, and legal jargon.

    oai_token-act-pair · gemini-2.0-flash

    first

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    migrationBuilder
    -0.85
    Fourth
    -0.72
    Sixth
    -0.67
    Fifth
    -0.67
    Seventh
    -0.66
    iprot
    -0.65
     Seventh
    -0.65
    
    -0.62
     Fourth
    -0.62
     NSCoder
    -0.61
    POSITIVE LOGITS
     first
    3.47
    first
    3.00
    First
    2.41
     first
    2.36
     FIRST
    2.25
     eerste
    2.23
     First
    2.16
     primero
    2.16
     ersten
    2.14
     primeiro
    2.14
    Activations Density 5.902%

    No Known Activations