© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12585
    Prev
    Next
    INDEX
    Explanations

    the word "relatively" combined with an adjective or noun

    oai_token-act-pair · gemini-2.0-flash

    atively

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    rstrip
    -0.53
     crossorigin
    -0.52
    angkut
    -0.49
     dips
    -0.48
     Gegenwart
    -0.48
    ījum
    -0.48
    ภัณฑ์
    -0.47
    zoeken
    -0.47
     otherwise
    -0.46
     [*]
    -0.46
    POSITIVE LOGITS
    mybatisplus
    0.76
    uxxxx
    0.73
     beginnetje
    0.68
     يتيمه
    0.66
    EDEFAULT
    0.63
    jago
    0.62
    NamedQueries
    0.60
     ویکی‌پدیا
    0.60
    RegistryLite
    0.59
    expandindo
    0.59
    Activations Density 1.079%

    No Known Activations