© 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. 13425
    Prev
    Next
    INDEX
    Explanations

    code-related, especially javascript code, including comments, code syntax and keywords

    oai_token-act-pair · gemini-2.0-flash

    non-standard or irregular coding patterns

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

    code context

    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
    ==
    -0.94
     ==
    -0.83
    ==-
    -0.76
    ]=='
    -0.73
    =="
    -0.71
    =='
    -0.71
    ==="
    -0.69
    ']==
    -0.67
     !=
    -0.66
    ]=="
    -0.65
    POSITIVE LOGITS
     تضيفلها
    0.74
    +#+#
    0.72
    RectangleBorder
    0.66
     سبورت
    0.62
     estimés
    0.60
     myſelf
    0.59
    TargetException
    0.59
     كومونز
    0.58
     HasFactory
    0.57
     ujednoznacz
    0.57
    Activations Density 1.380%

    No Known Activations