© 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. 7112
    Prev
    Next
    INDEX
    Explanations

    words and abbreviations related to scientific experiments involving rats, saline, and amino acid deficiencies.

    oai_token-act-pair · gemini-2.0-flash

    saliva

    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
     sal
    -2.47
     SAL
    -2.42
     Sal
    -2.38
    Sal
    -2.30
    SAL
    -2.22
    sal
    -2.05
     Salt
    -1.88
     SALT
    -1.79
     salt
    -1.77
    Salt
    -1.77
    POSITIVE LOGITS
    Hend
    0.54
     McCormack
    0.49
     Bho
    0.48
     Gwend
    0.47
     TextAppearance
    0.46
    孚
    0.46
     Hend
    0.45
     الاطلاع
    0.45
     Bevan
    0.45
    Autoritní
    0.43
    Activations Density 1.196%

    No Known Activations