© 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. 8924
    Prev
    Next
    INDEX
    Explanations

    words and phrases that suggest relationships between people

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · 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
    ^(@)
    -1.30
     itſelf
    -1.24
     ་་
    -1.23
     Forumite
    -1.21
     doubtnut
    -1.17
    ſelves
    -1.16
     ―――――
    -1.16
     ſind
    -1.16
    <unused6>
    -1.16
    <unused47>
    -1.16
    POSITIVE LOGITS
     européennes
    0.30
     zöld
    0.27
     religieuses
    0.27
     anciens
    0.26
     supérieures
    0.25
     pauvres
    0.25
    .
    0.25
     chré
    0.25
     helyzet
    0.24
     pracovní
    0.24
    Activations Density 10.586%

    No Known Activations