© 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. 16196
    Prev
    Next
    INDEX
    Explanations

    words related to organizations, locations or tools that have to fulfill a goal.

    oai_token-act-pair · gemini-2.0-flash

    caused by

    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
     مشين
    -0.70
     Jefus
    -0.69
     Мексичка
    -0.68
    ParallelGroup
    -0.67
     theſe
    -0.66
    ✨:
    -0.66
     ſeveral
    -0.65
    same
    -0.62
     Meksiku
    -0.61
     poffible
    -0.60
    POSITIVE LOGITS
     based
    1.42
     driven
    1.34
     inspired
    1.29
     fuelled
    1.25
     powered
    1.23
     fueled
    1.22
     backed
    1.19
     related
    1.17
     centered
    1.15
     funded
    1.13
    Activations Density 6.064%

    No Known Activations