© 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. 3210
    Prev
    Next
    INDEX
    Explanations

    words related to predictions about the future, as well as certain adjectives and adverbs.

    oai_token-act-pair · gemini-2.0-flash

    going

    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
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -1.00
     itſelf
    -0.98
    IntoConstraints
    -0.89
     Jefus
    -0.89
     Monfieur
    -0.88
     Efq
    -0.84
    ſelves
    -0.81
     raiſ
    -0.80
    matchCondition
    -0.80
     Diſ
    -0.78
    POSITIVE LOGITS
     seguito
    0.54
     Contrary
    0.52
    Thanx
    0.51
     Moreover
    0.50
     like
    0.49
    webElementXpaths
    0.49
    Kindly
    0.47
    irp
    0.47
     gdyż
    0.47
     skall
    0.47
    Activations Density 1.944%

    No Known Activations