© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11776
    Prev
    Next
    INDEX
    Explanations

    terms related to AWS IAM policies and Amazon ads

    oai_token-act-pair · gemini-2.0-flash

    ARN

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     الرياضيه
    -0.57
     okuyayım
    -0.50
     continúas
    -0.46
     tủ
    -0.43
    InteropServices
    -0.41
     消
    -0.41
    hyphen
    -0.41
    nige
    -0.40
     dục
    -0.40
     Interest
    -0.40
    POSITIVE LOGITS
     NSCoder
    0.79
     purpoſe
    0.76
     AssemblyTitle
    0.76
     perſon
    0.71
     sahiptir
    0.69
    jspb
    0.69
     reaſon
    0.66
     ſeveral
    0.66
    astéroïdes
    0.65
    "]));
    0.65
    Activations Density 1.309%

    No Known Activations