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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16302
    Prev
    Next
    INDEX
    Explanations

    words and phrases from the Portuguese language related to Javascript programming and error handling

    oai_token-act-pair · gemini-2.0-flash

    Portuguese text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    IsMutable
    -0.81
    UnusedPrivate
    -0.73
    Datuak
    -0.73
    BindingResult
    -0.69
     سكانية
    -0.69
    styleType
    -0.68
     henvisninger
    -0.64
    featureID
    -0.63
    interopRequire
    -0.63
    ModelSerializer
    -0.62
    POSITIVE LOGITS
    lé
    0.41
    heri
    0.38
     Reeves
    0.37
     lw
    0.36
    ahuila
    0.35
    ooka
    0.35
    íc
    0.35
    fmf
    0.35
    simus
    0.34
    CWE
    0.34
    Activations Density 0.458%

    No Known Activations