© 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. 11709
    Prev
    Next
    INDEX
    Explanations

    code snippets and JSON structures with specific keywords like "accordion", "button", "index", "schedules", "nodes", and "promises"

    oai_token-act-pair · gemini-2.0-flash

    software/code configuration files

    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
    san
    -0.54
    sur
    -0.52
    sho
    -0.50
    sz
    -0.49
    she
    -0.45
    sand
    -0.44
    sound
    -0.44
    skin
    -0.44
    sn
    -0.43
    som
    -0.43
    POSITIVE LOGITS
    CloseOperation
    0.81
    pecies
    0.76
    ystems
    0.71
    leeve
    0.69
    olve
    0.68
    ystem
    0.67
    pecific
    0.67
    heet
    0.66
    erver
    0.66
    earch
    0.66
    Activations Density 22.414%

    No Known Activations