© 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. 9237
    Prev
    Next
    INDEX
    Explanations

    the word "bit" and words associated with approximation

    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
     MainAxisSize
    -1.00
    parsedMessage
    -0.99
     CreateTagHelper
    -0.94
     EconPapers
    -0.87
     שוליים
    -0.86
     Anſ
    -0.83
     Theſe
    -0.83
     Monfieur
    -0.82
     theſe
    -0.81
    LookAnd
    -0.77
    POSITIVE LOGITS
    .
    0.60
    ,
    0.53
    -
    0.44
    มาก
    0.42
     lắm
    0.41
     greatly
    0.40
     sekali
    0.39
     when
    0.39
    开
    0.39
    나
    0.39
    Activations Density 0.444%

    No Known Activations