© 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. 13274
    Prev
    Next
    INDEX
    Explanations

    the word `reliable` while also sometimes activating on words related to technical/engineering fields

    oai_token-act-pair · gemini-2.0-flash

    reliable

    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
    Negative Logits
     itſelf
    -1.02
    ]--;
    -1.00
    Amicalement
    -0.97
    BibitemShut
    -0.96
    djangoproject
    -0.96
     سكانية
    -0.96
    ^(@)
    -0.95
    aarrggbb
    -0.91
     ―――――
    -0.91
    drawal
    -0.91
    POSITIVE LOGITS
    .
    0.75
    ar
    0.72
    t
    0.66
    m
    0.63
    but
    0.63
    and
    0.63
    la
    0.62
    1
    0.62
    2
    0.61
    r
    0.59
    Activations Density 1.706%

    No Known Activations