© 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. 470
    Prev
    Next
    INDEX
    Explanations

    the word "real" and several other words, but there doesn't seem to be a unifying theme

    oai_token-act-pair · 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
    Negative Logits
    mybatisplus
    -0.68
    ########.
    -0.64
     textStatus
    -0.63
    WebServlet
    -0.62
    $_['
    -0.61
    #
    -0.60
    Xna
    -0.60
     springfox
    -0.60
     StyleSheet
    -0.59
    adaptiveStyles
    -0.59
    POSITIVE LOGITS
     pourtant
    0.50
    uxxxx
    0.46
    farwyddwr
    0.45
     AssemblyCulture
    0.45
    FieldOffset
    0.43
     colspan
    0.43
    Mehr
    0.42
    RTSC
    0.42
     lisää
    0.42
    CopyWith
    0.41
    Activations Density 3.373%

    No Known Activations