© 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. 13932
    Prev
    Next
    INDEX
    Explanations

    equation labels

    oai_token-act-pair · gemini-2.0-flash

    eq

    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
    RenderAtEndOf
    -1.65
    ^(@)
    -1.56
     Efq
    -1.53
    BufferException
    -1.41
    Personensuche
    -1.39
    ]--;
    -1.38
    BibitemShut
    -1.33
     مشين
    -1.32
     beginnetje
    -1.30
    NUMX
    -1.27
    POSITIVE LOGITS
    ’
    0.85
    k
    0.79
    '
    0.77
    ,
    0.70
    h
    0.66
    f
    0.65
    U
    0.65
    <eos>
    0.64
    I
    0.64
    S
    0.63
    Activations Density 0.485%

    No Known Activations