Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 11990
    Prev
    Next
    INDEX
    Explanations

    words related to geometric location and neighbors, and code

    oai_token-act-pair · gemini-2.0-flash

    image processing algorithms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     betweenstory
    -0.55
    rawDesc
    -0.52
    GraphicsUnit
    -0.50
    ollectionView
    -0.50
    ORTH
    -0.49
    URATION
    -0.48
    ANTLR
    -0.47
    leet
    -0.47
     OnInit
    -0.47
    页面存档备份
    -0.47
    POSITIVE LOGITS
    dafx
    0.58
    Parcelize
    0.56
    enterOuterAlt
    0.55
    Datuak
    0.51
    DeleteBehavior
    0.50
    IPAC
    0.50
     يتيمه
    0.50
    migrationBuilder
    0.50
    SocketChannel
    0.49
    gonic
    0.47
    Activations Density 3.636%

    No Known Activations