© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2755
    Prev
    Next
    INDEX
    Explanations

    non-English words

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

    code snippets in programming languages and related phrases in different languages.

    oai_token-act-pair · gemini-2.0-flash

    Code/foreign languages

    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
    uszki
    -0.50
     sebaliknya
    -0.47
    Zunanje
    -0.47
    entendre
    -0.46
    requisites
    -0.46
    stdafx
    -0.46
     bfs
    -0.44
     Aguirre
    -0.44
     Gegenteil
    -0.43
    renia
    -0.42
    POSITIVE LOGITS
     Numerade
    0.60
    μένων
    0.59
    monių
    0.56
    ftagPool
    0.56
    álních
    0.55
    Diwedd
    0.54
    ικών
    0.53
    nych
    0.53
    тых
    0.52
    TagMode
    0.52
    Activations Density 0.352%

    No Known Activations