© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4080
    Prev
    Next
    INDEX
    Explanations

    variable names like "count," "tmp," "depth," "ar," and "contador".

    oai_token-act-pair · gemini-2.0-flash

    special character patterns or programming conventions

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

    say "++"

    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
    éc
    -0.51
    ynie
    -0.47
    hty
    -0.45
     informée
    -0.45
     einstellen
    -0.43
    iem
    -0.43
     asciug
    -0.43
     plan
    -0.43
    nen
    -0.43
    poca
    -0.42
    POSITIVE LOGITS
    libft
    0.83
    LookAnd
    0.81
    Rhestr
    0.79
    aarrggbb
    0.77
     مشين
    0.75
     Савезне
    0.75
     createState
    0.69
    Дереккөздер
    0.69
    +#+
    0.68
    DockStyle
    0.68
    Activations Density 0.505%

    No Known Activations