© 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. 6962
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with mobile apps

    oai_token-act-pair · gemini-2.0-flash

    verbs related to action

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

    acting

    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
    aarrggbb
    -0.65
    Хьажоргаш
    -0.63
    rifuge
    -0.60
    MessageTagHelper
    -0.59
    XmlAccessType
    -0.59
     encomp
    -0.57
    المشاركات
    -0.57
     Reſ
    -0.56
     enfans
    -0.56
    ilustrasi
    -0.54
    POSITIVE LOGITS
     acted
    0.66
    :✨
    0.64
     acting
    0.62
     let
    0.61
     working
    0.61
     acts
    0.60
    acts
    0.60
     act
    0.59
     allow
    0.57
     worked
    0.55
    Activations Density 2.586%

    No Known Activations