© 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. 7622
    Prev
    Next
    INDEX
    Explanations

    text from scientific publications defining an experiment

    oai_token-act-pair · gemini-2.0-flash

    questionnaires and measurements

    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
    AndEndTag
    -0.61
     surla
    -0.51
    __*/
    -0.51
    AddHtmlAttribute
    -0.49
     '\\;'
    -0.48
    fjspx
    -0.47
     PLWABN
    -0.47
     GenerationType
    -0.47
    írus
    -0.43
    الإنجليزية
    -0.42
    POSITIVE LOGITS
     Motivation
    0.57
    Motivation
    0.54
     RPA
    0.54
    xase
    0.54
     Reasoning
    0.52
    asan
    0.51
     linearity
    0.51
     词
    0.50
    enang
    0.50
     seriousness
    0.50
    Activations Density 23.094%

    No Known Activations