© 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. 3541
    Prev
    Next
    INDEX
    Explanations

    words and phrases that express that something is fair or just

    oai_token-act-pair · gemini-2.0-flash

    development in other languages

    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
    Obrázky
    -0.57
    CPtr
    -0.56
    FromArgb
    -0.53
    SharedCtor
    -0.50
    basicConfig
    -0.49
    pril
    -0.47
    TextHelper
    -0.45
    WhereInput
    -0.45
    providedIn
    -0.44
    IntoConstraints
    -0.44
    POSITIVE LOGITS
     development
    0.69
     sviluppo
    0.67
    veloppement
    0.65
     henvisninger
    0.63
    Development
    0.62
    development
    0.60
     développement
    0.59
     ontwikkeling
    0.59
    ImageContext
    0.58
     desarrollo
    0.57
    Activations Density 14.063%

    No Known Activations