© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 490
    Prev
    Next
    INDEX
    Explanations

    code-related keywords, especially those related to coordinates and transformations

    oai_token-act-pair · gemini-2.0-flash

    position coordinates

    np_max-act · 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
    RTSN
    -0.60
    Coordinates
    -0.59
     coordinates
    -0.58
    Coords
    -0.57
    CGRectMake
    -0.56
    pos
    -0.56
    coords
    -0.55
    Koordin
    -0.54
    Coord
    -0.54
    Bounds
    -0.54
    POSITIVE LOGITS
     unknownFields
    0.66
    EDEFAULT
    0.64
    setVerticalGroup
    0.63
    
    0.60
     "..\..\
    0.58
     correctes
    0.57
     tölt
    0.57
    RegressionTest
    0.55
    RUnlock
    0.55
    RetentionPolicy
    0.54
    Activations Density 14.310%

    No Known Activations