© 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. 423
    Prev
    Next
    INDEX
    Explanations

    the characters "wr" near periods, often in the context of parameters

    oai_token-act-pair · gemini-2.0-flash

    r

    np_max-act · 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
    <bos>
    -1.88
    '}>
    -0.64
    ThemeOverlay
    -0.59
    __':
    -0.54
    '
    -0.53
    `]
    -0.51
     the
    -0.51
    ’
    -0.51
    들이
    -0.50
    __":
    -0.49
    POSITIVE LOGITS
    PyExc
    0.68
     defaultstate
    0.67
    Hochspringen
    0.65
    flav
    0.64
     CreateTagHelper
    0.63
    RuleContext
    0.63
    WebElementEntity
    0.63
    gnition
    0.62
     continúas
    0.60
    tvguidetime
    0.60
    Activations Density 1.471%

    No Known Activations