© 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. 4297
    Prev
    Next
    INDEX
    Explanations

    Japanese text describing a failed attempt to execute code, potentially using Maven and encountering errors.

    oai_token-act-pair · gemini-2.0-flash

    programming-related terms

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

    Code and error messages

    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
     Мексичка
    -0.75
    StructEnd
    -0.75
    enumi
    -0.75
     estekak
    -0.74
    ThroughAttribute
    -0.73
     purpoſe
    -0.71
     ModelExpression
    -0.71
    Rhestr
    -0.69
    enderror
    -0.69
     ویکی‌پدیا
    -0.69
    POSITIVE LOGITS
    polation
    0.47
    willow
    0.41
    fputs
    0.40
     Power
    0.39
    survival
    0.39
    ttps
    0.38
     «
    0.35
     B
    0.35
    insertion
    0.34
     ‘
    0.34
    Activations Density 4.433%

    No Known Activations