© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3189
    Prev
    Next
    INDEX
    Explanations

    words or phrases that combine opposite states or meanings

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     en
    -0.66
     inf
    -0.65
     des
    -0.62
     de
    -0.62
     dé
    -0.60
     un
    -0.59
     En
    -0.59
    En
    -0.58
     au
    -0.56
     inde
    -0.56
    POSITIVE LOGITS
     feroit
    1.07
     purpoſe
    1.05
     avoient
    1.05
     scolaires
    1.02
     épis
    0.98
     étoient
    0.98
     سكانية
    0.97
     myſelf
    0.96
     ſtate
    0.92
     nationaux
    0.92
    Activations Density 2.163%

    No Known Activations