© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14624
    Prev
    Next
    INDEX
    Explanations

    positive adjectives

    oai_token-act-pair · gemini-2.0-flash

    positive adjectives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     amazing
    -1.52
     wonderful
    -1.52
     fantastic
    -1.43
     fabulous
    -1.25
     excellent
    -1.25
    wonderful
    -1.23
     marvelous
    -1.20
     marvellous
    -1.19
     awesome
    -1.18
    amazing
    -1.18
    POSITIVE LOGITS
     '\\;'
    0.90
     CreateTagHelper
    0.83
     ExecuteAsync
    0.78
    TagMode
    0.67
    IntoConstraints
    0.65
     PublicKey
    0.62
     Dage
    0.59
     onAnimation
    0.59
    icose
    0.59
     endforeach
    0.58
    Activations Density 2.245%

    No Known Activations