© 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. 9478
    Prev
    Next
    INDEX
    Explanations

    words related to progress and actions within projects or plans

    oai_token-act-pair · gemini-2.0-flash

    future events

    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
    HttpFoundation
    -0.69
    ˏ
    -0.65
    labus
    -0.63
    duled
    -0.62
     étoit
    -0.62
     Led
    -0.60
     attendre
    -0.59
    thar
    -0.59
    _'+
    -0.59
     auront
    -0.58
    POSITIVE LOGITS
    <bos>
    0.71
    AutoresizingMask
    0.60
     الرياضيه
    0.58
    xically
    0.55
     poveznice
    0.54
     actually
    0.50
    ponses
    0.48
     calendriers
    0.48
     насељу
    0.47
    actually
    0.47
    Activations Density 5.225%

    No Known Activations