© 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. 7459
    Prev
    Next
    INDEX
    Explanations

    Chinese characters describing dictionary compilation, especially suffixes and prefixes related to place names, math units, surnames, and regions

    oai_token-act-pair · gemini-2.0-flash

    Technical / code snippets

    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
     quæ
    -0.85
     enfans
    -0.75
     pleaſure
    -0.72
     houſe
    -0.70
     purpoſe
    -0.70
     ſtre
    -0.68
     ſtate
    -0.67
     stappen
    -0.67
     ſch
    -0.66
     esprits
    -0.66
    POSITIVE LOGITS
     sugges
    0.54
     мәкал
    0.54
     UNAM
    0.52
     RTA
    0.52
     PIM
    0.51
     Photoshop
    0.51
     catwalk
    0.50
    izability
    0.49
     SCM
    0.49
     dsl
    0.49
    Activations Density 1.079%

    No Known Activations