© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2687
    Prev
    Next
    INDEX
    Explanations

    a strange mix of words including named entities, adjectives, and seemingly unrelated words that have a slight connection to food, events, or locations

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    <bos>
    -0.68
    NOPQRST
    -0.65
    DrawerToggle
    -0.57
    conio
    -0.56
     تضيفلها
    -0.55
     portero
    -0.53
    Diwedd
    -0.50
    ViewChild
    -0.50
     kasarigan
    -0.50
    évaluateur
    -0.50
    POSITIVE LOGITS
    onedDateTime
    0.55
    traje
    0.50
     RESIDENCE
    0.49
    herself
    0.47
     UnityEngine
    0.47
    tawesome
    0.47
    fromnode
    0.46
     COLLEGE
    0.46
    ყ
    0.46
    abin
    0.46
    Activations Density 16.708%

    No Known Activations