© 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. 3150
    Prev
    Next
    INDEX
    Explanations

    mentions or descriptions of an animal's natural environment

    oai_token-act-pair · gemini-2.0-flash

    habitat

    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
     
    -1.23
    <bos>
    -1.14
      
    -1.00
     The
    -0.81
    ↵↵
    -0.81
    The
    -0.80
    ’
    -0.79
    1
    -0.78
    2
    -0.76
    ↵
    -0.74
    POSITIVE LOGITS
     MainAxisSize
    1.30
    ^(@)
    1.23
     Мексичка
    1.18
    PyExc
    1.13
    Datuak
    1.10
     Majefty
    1.10
     snippetHide
    1.09
    neſs
    1.09
    ReusableCell
    1.09
    ագրություններ
    1.09
    Activations Density 1.814%

    No Known Activations