© 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. 6782
    Prev
    Next
    INDEX
    Explanations

    mentions of charitable organizations or actions

    oai_token-act-pair · gemini-2.0-flash

    charity

    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
     
    -1.43
    ,
    -1.31
    ing
    -1.31
      
    -1.26
     (
    -1.24
    ↵
    -1.18
    .
    -1.13
    ↵↵
    -1.10
     and
    -1.09
     for
    -1.09
    POSITIVE LOGITS
     myſelf
    2.17
     Efq
    2.09
     ſind
    2.08
     Monfieur
    2.02
     Theſe
    1.95
     ―――――
    1.89
     themſelves
    1.88
    ^(@)
    1.87
     iſt
    1.86
     $_"
    1.84
    Activations Density 1.668%

    No Known Activations