© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12453
    Prev
    Next
    INDEX
    Explanations

    words relating to technology and research papers

    oai_token-act-pair · gemini-2.0-flash

    proposed framework/algorithm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    usermodel
    -0.56
    TypedDataSet
    -0.56
    klärung
    -0.50
     propOrder
    -0.50
    nads
    -0.48
     sub
    -0.47
     sophistic
    -0.46
    soph
    -0.46
    essoas
    -0.46
    ​​​​
    -0.45
    POSITIVE LOGITS
    Portail
    0.66
    .*")]
    0.59
     Majefty
    0.59
     comunit
    0.56
    Gemeinden
    0.54
     ramos
    0.53
    LookAnd
    0.53
     Stationary
    0.51
     Diſ
    0.51
     equalTo
    0.51
    Activations Density 6.619%

    No Known Activations