© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3341
    Prev
    Next
    INDEX
    Explanations

    initials of people in a formal context

    oai_token-act-pair · gemini-2.0-flash

    M

    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
    MENAFN
    -0.62
    sidemargin
    -0.61
     propOrder
    -0.60
    はじめに
    -0.58
    addGap
    -0.57
    XmlAccessType
    -0.57
    bootstrapcdn
    -0.55
    EDEFAULT
    -0.53
     Normdatei
    -0.53
     rég
    -0.52
    POSITIVE LOGITS
    ArrowToggle
    0.58
    ыгана
    0.55
    setVerticalGroup
    0.54
    posables
    0.52
     NUKAT
    0.51
    ucoup
    0.50
     garda
    0.49
    exels
    0.48
    IGENCE
    0.48
     underval
    0.48
    Activations Density 0.259%

    No Known Activations