© 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. 15268
    Prev
    Next
    INDEX
    Explanations

    XML or XML-like tag names that might specify versions or layout properties, and some color names

    oai_token-act-pair · gemini-2.0-flash

    artifactId

    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
    RegressionTest
    -0.85
    parsedMessage
    -0.75
    曖昧さ回避
    -0.75
    GEBURTSDATUM
    -0.63
     חיצוניים
    -0.60
     дописавши
    -0.59
    CPtr
    -0.59
    StoreMessageInfo
    -0.57
    __*/
    -0.57
    NameInMap
    -0.55
    POSITIVE LOGITS
    ercises
    0.55
    endwhile
    0.53
    beginTransaction
    0.53
    umman
    0.51
    DrawerLayout
    0.51
    glLoadIdentity
    0.50
    volut
    0.48
    duled
    0.47
     ballast
    0.47
    )="
    0.47
    Activations Density 0.049%

    No Known Activations