© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6815
    Prev
    Next
    INDEX
    Explanations

    the word "allege" and forms of that word like "alleges", "alleged", and "allegations."

    oai_token-act-pair · gemini-2.0-flash

    alleged

    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
     myſelf
    -2.94
     Monfieur
    -2.94
     itſelf
    -2.86
     Efq
    -2.81
     purpoſe
    -2.77
     houſe
    -2.73
     Theſe
    -2.73
     Houſe
    -2.69
     Jefus
    -2.66
     Majefty
    -2.63
    POSITIVE LOGITS
     
    1.51
    ↵↵
    1.38
      
    1.37
    ↵
    1.29
     The
    1.24
     (
    1.22
     A
    1.15
    <eos>
    1.10
     I
    1.10
     ‘
    1.09
    Activations Density 0.947%

    No Known Activations