© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14573
    Prev
    Next
    INDEX
    Explanations

    programming code, statistical reports, and mathematical formulas

    oai_token-act-pair · gemini-2.0-flash

    scientific observations/iterations

    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
     المعيارى
    -0.55
     AttributeSet
    -0.47
    BGR
    -0.47
    readystatechange
    -0.46
     defStyleAttr
    -0.45
     ($('#
    -0.44
    UserScript
    -0.43
     newBuilder
    -0.42
    BuildContext
    -0.42
    rogens
    -0.42
    POSITIVE LOGITS
    awtextra
    0.66
    Diwedd
    0.64
    titleMargin
    0.54
    <bos>
    0.52
     utafitiHapana
    0.52
    ม้
    0.52
     fallait
    0.51
    ApiModelProperty
    0.50
    +#+#
    0.50
    fieldId
    0.50
    Activations Density 1.761%

    No Known Activations