© 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. 11716
    Prev
    Next
    INDEX
    Explanations

    words that are relevant within conversational writing in blog posts.

    oai_token-act-pair · gemini-2.0-flash

    AppComponent

    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
     RL
    -0.80
     LR
    -0.79
    RL
    -0.78
    rl
    -0.77
    LR
    -0.77
    Lr
    -0.75
    lr
    -0.72
     rl
    -0.70
     lr
    -0.70
    getL
    -0.69
    POSITIVE LOGITS
     OMITBAD
    0.49
     AppComponent
    0.47
    tableFuture
    0.46
     مشين
    0.45
    FTFY
    0.42
    Sucesor
    0.42
    قایناقلار
    0.41
    ViewFeatures
    0.41
     akka
    0.40
     SafeMath
    0.40
    Activations Density 72.725%

    No Known Activations