© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8486
    Prev
    Next
    INDEX
    Explanations

    the word "anymore" and "father."

    oai_token-act-pair · gemini-2.0-flash

    anymore

    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
    -1.82
     Efq
    -1.78
     Monfieur
    -1.60
    tvguidetime
    -1.59
     Majefty
    -1.55
     snippetHide
    -1.55
     pleaſure
    -1.54
     himſelf
    -1.53
     Theſe
    -1.52
     Forumite
    -1.51
    POSITIVE LOGITS
    <bos>
    1.62
    ↵↵
    1.23
    <eos>
    1.10
    ↵
    1.05
     The
    0.95
     P
    0.86
      
    0.84
     
    0.82
    P
    0.81
       
    0.81
    Activations Density 0.768%

    No Known Activations