© 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. 12763
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to flower arrangements, gifts and delivery services

    oai_token-act-pair · gemini-2.0-flash

    flowers and plants

    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
     flower
    -1.98
     Flower
    -1.90
     ROSE
    -1.85
     Rose
    -1.81
     flowers
    -1.80
     rose
    -1.80
    Flower
    -1.76
     FLOWER
    -1.73
     Flowers
    -1.73
     roses
    -1.71
    POSITIVE LOGITS
     Haddad
    0.57
     Acapulco
    0.50
    opardi
    0.48
     Nader
    0.47
    acap
    0.46
     Tapia
    0.46
     становника
    0.45
     Battista
    0.42
    ANTLR
    0.42
     Generales
    0.42
    Activations Density 1.401%

    No Known Activations