© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2448
    Prev
    Next
    INDEX
    Explanations

    coding symbols and abbreviations

    oai_token-act-pair · gemini-2.0-flash

    Code and statistics phrases

    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
     ins
    -0.63
     input
    -0.62
    input
    -0.60
     imports
    -0.60
    intern
    -0.59
     international
    -0.59
     id
    -0.57
    international
    -0.57
    instance
    -0.57
     incu
    -0.56
    POSITIVE LOGITS
     تضيفلها
    0.70
     متعلقه
    0.68
     Италијани
    0.59
     kwal
    0.58
    سطس
    0.53
    II
    0.52
    clable
    0.51
     protoimpl
    0.50
    hoea
    0.50
    𝐼
    0.50
    Activations Density 3.876%

    No Known Activations