© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15254
    Prev
    Next
    INDEX
    Explanations

    strings of characters composed of digits, hyphens, and some letters.

    oai_token-act-pair · gemini-2.0-flash

    words and terms from programming and markup languages

    np_token-act-pair-logits · gpt-4o-mini

    Code and data snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    CloseOperation
    -0.58
    nthesis
    -0.54
    ufnahme
    -0.54
    enoid
    -0.54
    dây
    -0.53
     dégâts
    -0.53
    charpe
    -0.52
    ποτε
    -0.51
    Жен
    -0.51
     antaranya
    -0.51
    POSITIVE LOGITS
     chi̍t
    0.59
    TextWatcher
    0.54
    Παραπομπές
    0.52
     transférez
    0.51
    tagHelperRunner
    0.50
    ngdoc
    0.49
     \%}$
    0.48
    LayoutInflater
    0.48
    GEBURTSDATUM
    0.47
     ProtoMessage
    0.46
    Activations Density 5.109%

    No Known Activations