© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6566
    Prev
    Next
    INDEX
    Explanations

    words related to travel, pathways, and the names "Rider", "Hero", or "Voyager"

    oai_token-act-pair · gemini-2.0-flash

    Kamen Rider

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    SerializedName
    -0.68
     single
    -0.57
    ahalli
    -0.54
    single
    -0.50
    machus
    -0.50
    rawDesc
    -0.50
    djangoproject
    -0.50
     jScrollPane
    -0.49
    ExceptionHandler
    -0.48
    LOY
    -0.47
    POSITIVE LOGITS
    <bos>
    0.81
    tagli
    0.71
     EconPapers
    0.61
     ویکی‌آمباردا
    0.59
     toured
    0.59
    }-${
    0.58
     ſind
    0.57
     useCallback
    0.57
     nød
    0.56
     intelligible
    0.56
    Activations Density 1.335%

    No Known Activations