© 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. 5371
    Prev
    Next
    INDEX
    Explanations

    words related to sandwiches, condiments, and hot food

    oai_token-act-pair · gemini-2.0-flash

    food and recipes

    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
    issau
    -0.56
    RectangleBorder
    -0.52
    \{\\
    -0.51
     techniczne
    -0.46
     InputDecoration
    -0.46
    itect
    -0.45
    :+:
    -0.45
    يتها
    -0.45
    phazard
    -0.44
     fleur
    -0.44
    POSITIVE LOGITS
    ⓧ
    0.76
    SourceChecksum
    0.71
    ValueStyle
    0.68
    ViewImports
    0.63
    RegistryLite
    0.63
    /***/
    0.57
    Démographie
    0.56
    AndroidJUnit
    0.56
     Grub
    0.52
     Laid
    0.52
    Activations Density 2.995%

    No Known Activations