© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7255
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to official announcements, reports, and recordings

    oai_token-act-pair · gemini-2.0-flash

    phrases related to formal statements

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

    statement

    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
     HasFactory
    -0.75
    uisine
    -0.68
    ttemberg
    -0.66
     typelib
    -0.63
    imanapun
    -0.62
    الحياه
    -0.61
     GenerationType
    -0.61
     '\\;'
    -0.61
     iprot
    -0.60
     ?>>
    -0.60
    POSITIVE LOGITS
     taken
    0.60
     obtained
    0.50
     acquired
    0.50
     distanciation
    0.49
     provided
    0.48
    aarrggbb
    0.48
     shared
    0.48
     ordered
    0.46
     made
    0.46
     brought
    0.46
    Activations Density 2.462%

    No Known Activations