© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 4896
    Prev
    Next
    INDEX
    Explanations

    conjunctions, pronouns, and articles used in storytelling

    oai_token-act-pair · 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
     He
    -3.20
    He
    -2.88
     His
    -2.17
    His
    -2.16
     Он
    -1.77
     Him
    -1.65
     Himself
    -1.57
     HE
    -1.46
    he
    -1.45
     him
    -1.43
    POSITIVE LOGITS
    AddTagHelper
    0.58
    \{\\
    0.57
    ContentAsync
    0.54
    вање
    0.51
    िखित
    0.51
    WaitGroup
    0.50
    stdc
    0.50
    UnitTesting
    0.49
    assertj
    0.49
    ellino
    0.48
    Activations Density 8.585%

    No Known Activations