© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9026
    Prev
    Next
    INDEX
    Explanations

    the word "Indicium" and the substring "indians"

    oai_token-act-pair · gemini-2.0-flash

    software/database documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     تضيفلها
    -0.64
     sociali
    -0.59
    BindingResult
    -0.56
     dipl
    -0.55
     Pelop
    -0.51
     Njema
    -0.51
     Prosperity
    -0.51
     compé
    -0.51
     Dialogue
    -0.50
    farin
    -0.50
    POSITIVE LOGITS
     Indians
    0.93
    Indians
    0.91
     Indian
    0.88
     indices
    0.87
     India
    0.84
     Indias
    0.81
    INDIAN
    0.81
    Indian
    0.80
     indian
    0.80
     index
    0.79
    Activations Density 0.871%

    No Known Activations