© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11697
    Prev
    Next
    INDEX
    Explanations

    words that indicate a level of something and also some names

    oai_token-act-pair · gemini-2.0-flash

    org

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    tvguidetime
    -1.10
     CreateTagHelper
    -1.04
    ंदीखरीदारी
    -1.02
     protoimpl
    -0.98
    ValueStyle
    -0.95
    httphttps
    -0.95
    findpost
    -0.92
    IsContent
    -0.91
     IBOutlet
    -0.91
     محفوظة
    -0.85
    POSITIVE LOGITS
     org
    1.03
    org
    0.98
    ORG
    0.77
    orgi
    0.73
     Or
    0.72
    Org
    0.69
     deb
    0.68
    Or
    0.62
     Org
    0.55
     ORG
    0.54
    Activations Density 2.641%

    No Known Activations