© 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. 4592
    Prev
    Next
    INDEX
    Explanations

    instances of trying something and discussing experiences

    oai_token-act-pair · gemini-2.0-flash

    giving something a try

    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
    Negative Logits
     JpaRepository
    -0.75
    
    -0.75
     continúas
    -0.74
    ConstraintMaker
    -0.70
    SpringBootTest
    -0.70
    קישורים
    -0.66
    httphttps
    -0.65
     eenige
    -0.65
    Personendaten
    -0.65
    johtaja
    -0.64
    POSITIVE LOGITS
    <bos>
    0.67
     ab
    0.49
     purchase
    0.48
     would
    0.46
    consulté
    0.44
     it
    0.42
    ab
    0.42
    '
    0.42
     tila
    0.42
    ch
    0.41
    Activations Density 1.555%

    No Known Activations