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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8487
    Prev
    Next
    INDEX
    Explanations

    vocabulary related to celebrities, their relationships, and financial details

    oai_token-act-pair · gemini-2.0-flash

    names

    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
    matchCondition
    -0.76
    IndentedString
    -0.72
     nahilalakip
    -0.69
     ویکی‌پدی
    -0.69
    ionario
    -0.68
    RegistryLite
    -0.67
    setVerticalGroup
    -0.67
     resourceCulture
    -0.65
    tonsoft
    -0.65
    SerializedName
    -0.65
    POSITIVE LOGITS
     Lenny
    0.54
     Heidi
    0.52
     Brody
    0.51
     Camila
    0.50
     gigi
    0.49
    最快更新
    0.48
     Britney
    0.48
     Brandi
    0.47
     Kendrick
    0.46
     Patti
    0.46
    Activations Density 34.668%

    No Known Activations