© 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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7795
    Prev
    Next
    INDEX
    Explanations

    words that are positive or relative to the concept of "high" or "superior" or "new"

    oai_token-act-pair · gemini-2.0-flash

    Importance and contrast

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    databind
    -0.65
    Carriera
    -0.56
    EReference
    -0.55
    CORBA
    -0.52
     Pomona
    -0.52
    ExtendWith
    -0.52
     Bann
    -0.51
    UrlResolution
    -0.51
    存于互联网档案馆
    -0.49
     türlü
    -0.49
    POSITIVE LOGITS
    }))
    
    0.72
     distanciation
    0.72
    FunctionFlags
    0.71
     Democrá
    0.66
    ⇑
    0.65
    igreja
    0.61
    `.`
    0.60
    irmed
    0.59
     jurisdic
    0.57
    peq
    0.57
    Activations Density 2.688%

    No Known Activations