© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14728
    Prev
    Next
    INDEX
    Explanations

    adjectives related to physical appearance or visual description

    oai_token-act-pair · gemini-2.0-flash

    Golden, warm colors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Hanks
    -0.53
    hidupan
    -0.52
    السكان
    -0.51
     Leading
    -0.51
     quæ
    -0.50
     suivez
    -0.50
     alimentaires
    -0.50
     alimentaire
    -0.49
     avoient
    -0.49
    اجة
    -0.49
    POSITIVE LOGITS
     amber
    0.72
     AssemblyCulture
    0.64
     golden
    0.61
     warm
    0.60
     aub
    0.59
     caramel
    0.57
     gold
    0.54
     warming
    0.53
     rich
    0.53
    car
    0.53
    Activations Density 1.198%

    No Known Activations