© 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. 14192
    Prev
    Next
    INDEX
    Explanations

    adjectives related to length of time or size

    oai_token-act-pair · gemini-2.0-flash

    durations

    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
     trips
    -1.14
     conferences
    -1.04
     rallies
    -1.03
     tours
    -1.01
     campaigns
    -0.98
     sessions
    -0.97
     contests
    -0.97
     Trips
    -0.95
    ⓧ
    -0.94
     fights
    -0.94
    POSITIVE LOGITS
     dieux
    0.55
     modalités
    0.42
     vœux
    0.42
     básicas
    0.41
    enquête
    0.40
     icônes
    0.40
     decorativas
    0.40
     critères
    0.40
    zzazione
    0.40
     dégâts
    0.40
    Activations Density 2.291%

    No Known Activations