© 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. 12773
    Prev
    Next
    INDEX
    Explanations

    Java or Kotlin import statements

    oai_token-act-pair · gemini-2.0-flash

    Code imports

    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
     إنها
    -0.40
     <<<<<<<<<<<<<<
    -0.38
    VIAF
    -0.37
    ail
    -0.37
     ga
    -0.36
     إنه
    -0.35
    celotti
    -0.35
    feira
    -0.35
    chaun
    -0.35
    acy
    -0.34
    POSITIVE LOGITS
    B
    0.55
    Au
    0.50
    ContentAsync
    0.50
    D
    0.49
    ItemBackground
    0.49
    Cas
    0.49
     Anak
    0.48
     Bor
    0.47
    AutoresizingMask
    0.47
     Arch
    0.47
    Activations Density 22.534%

    No Known Activations