© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11867
    Prev
    Next
    INDEX
    Explanations

    uses of the first person and second person, and possessives, as well as some references to literature and surgery

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    np_max-act-logits · gemini-2.0-flash

    French fragments

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     ་་
    -0.33
     ECR
    -0.33
     PDC
    -0.33
     photolibrary
    -0.32
     [?]
    -0.31
     DCP
    -0.31
     FMS
    -0.31
     BOP
    -0.31
     CTP
    -0.31
     GDR
    -0.31
    POSITIVE LOGITS
     démocr
    0.63
     varandra
    0.59
     avoient
    0.57
     supérieurs
    0.56
     réguli
    0.56
     supérieures
    0.56
     enfans
    0.56
     chré
    0.55
     financières
    0.54
     étoient
    0.53
    Activations Density 49.930%

    No Known Activations