© 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. 14713
    Prev
    Next
    INDEX
    Explanations

    positive feelings and experiences

    oai_token-act-pair · gemini-2.0-flash

    location or activity

    np_max-act-logits · gemini-2.0-flash
    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
     thinking
    -2.00
     Thinking
    -1.74
    Thinking
    -1.65
    thinking
    -1.61
     knowing
    -1.56
     hoping
    -1.52
     believing
    -1.43
    knowing
    -1.38
     wondering
    -1.38
     Knowing
    -1.36
    POSITIVE LOGITS
    PhysRevLett
    0.66
     ویکی‌پدیای
    0.65
    AccessorTable
    0.62
    addCriterion
    0.60
     FishBase
    0.59
     kaarangay
    0.56
     Valverde
    0.54
     betweenstory
    0.53
    Gruß
    0.52
    ruik
    0.51
    Activations Density 4.417%

    No Known Activations