© 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. 9451
    Prev
    Next
    INDEX
    Explanations

    words that end with "past" and words that indicate a change of state or are beyond something

    oai_token-act-pair · gemini-2.0-flash

    past

    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>
    -0.63
     encarga
    -0.61
    nestjs
    -0.56
     Teufel
    -0.56
     automatico
    -0.55
    FieldBuilder
    -0.54
     estimés
    -0.51
    styleable
    -0.50
     kaynağından
    -0.50
     MonoBehaviour
    -0.50
    POSITIVE LOGITS
    PASS
    0.88
     Pass
    0.87
     PASS
    0.82
    pass
    0.80
     pass
    0.80
    Passing
    0.78
    Pass
    0.77
     Passed
    0.75
    passing
    0.75
    passes
    0.73
    Activations Density 1.424%

    No Known Activations