© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14090
    Prev
    Next
    INDEX
    Explanations

    references to files with the ".txt" extension

    oai_token-act-pair · gemini-2.0-flash

    txt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Shakspeare
    -0.76
     nocturno
    -0.76
     imprimible
    -0.72
    idän
    -0.65
     pleaſure
    -0.65
     santai
    -0.63
     vermelha
    -0.61
     fratelli
    -0.61
     dourada
    -0.60
     kanssa
    -0.59
    POSITIVE LOGITS
    oneofs
    0.66
    numerusform
    0.65
    UserScript
    0.65
    Portale
    0.64
    SharedDtor
    0.61
     kaarangay
    0.61
     EXAMINATION
    0.60
    haped
    0.59
     (=
    0.59
     Initialized
    0.58
    Activations Density 1.724%

    No Known Activations