© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6446
    Prev
    Next
    INDEX
    Explanations

    the words "tribe", "tribes", and "tribal", and "culture"

    oai_token-act-pair · gemini-2.0-flash

    tribes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     
    -1.25
     I
    -1.16
     (
    -1.09
     F
    -1.03
     de
    -0.99
     A
    -0.94
     R
    -0.93
     C
    -0.93
     P
    -0.91
     H
    -0.91
    POSITIVE LOGITS
     ſche
    1.77
     ainfi
    1.75
     avoient
    1.73
     Monfieur
    1.73
     étoient
    1.73
     itſelf
    1.73
     ſtate
    1.71
     auroit
    1.70
     étoit
    1.66
     enfans
    1.64
    Activations Density 1.480%

    No Known Activations