© 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. 4101
    Prev
    Next
    INDEX
    Explanations

    code snippets and related comments

    oai_token-act-pair · gemini-2.0-flash

    Code and Chinese 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
     OFDb
    -0.77
     Réponses
    -0.77
    expandindo
    -0.77
     typelib
    -0.76
     дописавши
    -0.69
     виправивши
    -0.69
    ]();
    -0.69
    Personensuche
    -0.68
     EconPapers
    -0.68
    ConstraintMaker
    -0.67
    POSITIVE LOGITS
     会
    0.39
     开
    0.35
     相
    0.35
     同
    0.33
     根据
    0.33
     万
    0.31
     流
    0.31
     都
    0.31
     配
    0.30
     重
    0.30
    Activations Density 2.955%

    No Known Activations