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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12573
    Prev
    Next
    INDEX
    Explanations

    numerical data.

    oai_token-act-pair · gemini-2.0-flash

    special characters or non-English words

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

    Data and code 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
    scriptcase
    -0.61
    endpush
    -0.55
     tartalomajánló
    -0.54
    InitVars
    -0.52
    ianum
    -0.52
    digm
    -0.52
     <>",
    -0.52
     kask
    -0.50
    EndGlobal
    -0.49
     ویکی‌پدیای
    -0.48
    POSITIVE LOGITS
     Créez
    0.61
    الحياه
    0.58
     pinulongan
    0.55
    InputTagHelper
    0.54
    }],
    0.54
     <=",
    0.53
     Borel
    0.52
    FormTagHelper
    0.51
    下载附件
    0.50
    DJANGO
    0.49
    Activations Density 0.602%

    No Known Activations