© 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. 13841
    Prev
    Next
    INDEX
    Explanations

    time increments, specifically "year" and "decade," and a couple of other random words

    oai_token-act-pair · gemini-2.0-flash

    terms related to time and user interaction

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

    structure or arrangement

    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
     initComponents
    -0.69
    ThroughAttribute
    -0.54
    nutie
    -0.52
     урна
    -0.48
     moindre
    -0.47
    ạc
    -0.46
     utafitiHapana
    -0.46
    sifs
    -0.45
     CommonModule
    -0.45
    yntaxException
    -0.44
    POSITIVE LOGITS
     Roskov
    0.69
     by
    0.65
     noDo
    0.64
     vPvB
    0.63
    webElementXpaths
    0.62
     CreateTagHelper
    0.61
    Gambas
    0.59
    :✨
    0.58
    SharedCtor
    0.57
     الاطلاع
    0.56
    Activations Density 0.660%

    No Known Activations