© 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. 3560
    Prev
    Next
    INDEX
    Explanations

    words and phrases in legal and medical contexts

    oai_token-act-pair · gemini-2.0-flash

    to begin

    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
     sat
    -0.59
     closed
    -0.59
    RetentionPolicy
    -0.56
    CppMethod
    -0.56
     advanced
    -0.53
    advanced
    -0.53
    URLException
    -0.52
    gouv
    -0.52
     extended
    -0.49
     Closed
    -0.49
    POSITIVE LOGITS
     entered
    0.72
     begun
    0.71
     started
    0.68
     Started
    0.68
     commenced
    0.68
     launched
    0.66
    started
    0.66
     began
    0.65
     begon
    0.62
     Arrived
    0.62
    Activations Density 9.169%

    No Known Activations