© 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. 613
    Prev
    Next
    INDEX
    Explanations

    word fragments that have a vowel or y followed by two or three consonants

    oai_token-act-pair · gemini-2.0-flash

    lyn

    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
    n
    -2.27
     n
    -2.23
    N
    -1.40
     N
    -1.29
    ｎ
    -1.26
    𝑛
    -1.10
    getN
    -1.05
    ɴ
    -0.98
    setN
    -0.97
    𝗻
    -0.96
    POSITIVE LOGITS
     تضيفلها
    0.59
    UserScript
    0.57
     protoimpl
    0.57
    发表于
    0.56
     oprot
    0.51
     wireType
    0.49
    TagHelpers
    0.48
    Spoljašnje
    0.47
    ciclo
    0.45
    RepeatedField
    0.44
    Activations Density 0.944%

    No Known Activations