© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12923
    Prev
    Next
    INDEX
    Explanations

    code snippets and technical language related to web development and programming.

    oai_token-act-pair · gemini-2.0-flash

    code and foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    RenderAtEndOf
    -1.52
    OGND
    -1.46
     تضيفلها
    -1.41
     autorytatywna
    -1.40
    tagHelperRunner
    -1.33
    IntoConstraints
    -1.33
     المعيارى
    -1.32
    parsedMessage
    -1.32
     disambiguazione
    -1.30
    StructEnd
    -1.30
    POSITIVE LOGITS
    <bos>
    -0.16
     např
    -0.38
     reli
    -0.39
    俗
    -0.39
     derro
    -0.39
     واست
    -0.39
     následu
    -0.39
     современ
    -0.39
     تعرض
    -0.39
    関連記事
    -0.40
    Activations Density 13.859%

    No Known Activations