© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10260
    Prev
    Next
    INDEX
    Explanations

    occurrences of "idea" near words indicating possession ("the", "my", numbers, names)

    oai_token-act-pair · gemini-2.0-flash

    idea

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    Autoritní
    -0.79
     <=",
    -0.68
    enderror
    -0.63
    DetailComponent
    -0.59
    ⓧ
    -0.58
     intptr
    -0.57
    NameInMap
    -0.57
     *)__
    -0.56
    Slf
    -0.56
    delwed
    -0.54
    POSITIVE LOGITS
     insight
    0.68
     flash
    0.63
     idea
    0.63
    brilliant
    0.63
     brilliant
    0.59
     brilli
    0.58
     bright
    0.57
     thought
    0.56
     brilliance
    0.56
    Bright
    0.56
    Activations Density 1.819%

    No Known Activations