© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2618
    Prev
    Next
    INDEX
    Explanations

    Spanish words and code snippets

    oai_token-act-pair · gemini-2.0-flash

    software code

    np_max-act-logits · gemini-2.0-flash

    Spanish function words

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    المشاركات
    -0.69
    awtextra
    -0.65
    Jegyzetek
    -0.61
    setVerticalGroup
    -0.59
    UnusedPrivate
    -0.59
    Datuak
    -0.58
    VolleyError
    -0.57
    govt
    -0.57
    BrowserModule
    -0.56
     صوتيه
    -0.56
    POSITIVE LOGITS
    ])));
    0.47
    hadoop
    0.45
    GeneratedValue
    0.44
    hilation
    0.44
    oftware
    0.43
    BeforeMethod
    0.42
    ∞
    0.41
     jub
    0.40
    FormTagHelper
    0.40
    XmlAttribute
    0.39
    Activations Density 0.278%

    No Known Activations