© 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. 9440
    Prev
    Next
    INDEX
    Explanations

    various kinds of parentheses

    oai_token-act-pair · gemini-2.0-flash

    opening parentheses

    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
     (
    -1.46
     ("
    -1.43
     ('
    -1.42
     (“
    -1.32
     ($
    -1.23
     (‘
    -1.20
     (-
    -1.20
     («
    -1.16
     [
    -1.16
     and
    -1.15
    POSITIVE LOGITS
     Monfieur
    2.30
     myſelf
    2.22
     itſelf
    2.22
     Efq
    2.19
     Shakspeare
    2.09
     Jefus
    2.08
     pleaſure
    2.05
     Reſ
    2.03
     Theſe
    2.03
     purpoſe
    2.00
    Activations Density 1.978%

    No Known Activations