© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5613
    Prev
    Next
    INDEX
    Explanations

    language related to scientific and statistical analysis and reasoning

    oai_token-act-pair · gemini-2.0-flash

    terms related to phylogenetic trees

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    gdala
    -0.69
    transQ
    -0.62
     onlyOwner
    -0.61
     AssemblyTitle
    -0.61
    Portale
    -0.60
    তথ্যসূত্র
    -0.60
    InstanceState
    -0.60
    abetes
    -0.59
    rungsseite
    -0.55
    Etsy
    -0.55
    POSITIVE LOGITS
    +#+
    0.60
     support
    0.60
     Support
    0.59
     tree
    0.58
    树
    0.57
    樹
    0.55
     Tree
    0.54
    upport
    0.53
     Grass
    0.52
    บรร
    0.51
    Activations Density 5.206%

    No Known Activations