© 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. 11376
    Prev
    Next
    INDEX
    Explanations

    technical or academic language, particularly related to research papers, code, or formal processes

    oai_token-act-pair · gemini-2.0-flash

    data evaluation and selection

    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
     following
    -0.77
    Using
    -0.75
     using
    -0.74
     Using
    -0.73
     follow
    -0.71
     Following
    -0.70
    Following
    -0.69
    following
    -0.69
    using
    -0.67
     USING
    -0.66
    POSITIVE LOGITS
    bootstrapcdn
    0.69
    Hentet
    0.66
     дописавши
    0.62
     démocratique
    0.58
    brainly
    0.54
    neden
    0.53
    原始内容存档于
    0.53
     étoit
    0.52
    benhavn
    0.52
    Truthy
    0.51
    Activations Density 19.585%

    No Known Activations