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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1766
    Prev
    Next
    INDEX
    Explanations

    proper nouns, technical terms and numerical values

    oai_token-act-pair · gemini-2.0-flash

    Words ending in "-er"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ORO
    -0.40
     domic
    -0.37
    戒
    -0.36
    Arc
    -0.35
     parvenir
    -0.35
     craindre
    -0.34
    ARN
    -0.34
    GraphicsUnit
    -0.33
     McDonnell
    -0.33
     conclure
    -0.33
    POSITIVE LOGITS
     Cutter
    1.11
     Translator
    1.09
     Interpreter
    1.08
    Searcher
    1.07
     Installer
    1.07
     Painter
    1.07
     Splitter
    1.06
     Mover
    1.05
     Dreamer
    1.05
     walker
    1.05
    Activations Density 27.625%

    No Known Activations