© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14322
    Prev
    Next
    INDEX
    Explanations

    punctuation and common words that often appear in quoted text

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     itſelf
    -1.02
     ―――――
    -0.91
     resourceCulture
    -0.88
    !("{}",
    -0.85
    NUMX
    -0.85
    __':
    -0.84
    OGND
    -0.83
     initComponents
    -0.83
     ――――
    -0.83
    `,
    -0.82
    POSITIVE LOGITS
     particularly
    0.69
     is
    0.63
    and
    0.60
     especially
    0.59
     was
    0.52
     has
    0.50
    de
    0.50
    if
    0.50
     K
    0.49
     its
    0.48
    Activations Density 17.673%

    No Known Activations