© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14840
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "fellow"

    oai_token-act-pair · gemini-2.0-flash

    fellow

    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
    <eos>
    -1.78
     
    -1.71
     (
    -1.60
      
    -1.48
     I
    -1.46
     C
    -1.42
     N
    -1.42
    ↵
    -1.41
    ↵↵
    -1.40
     a
    -1.36
    POSITIVE LOGITS
     myſelf
    3.45
     Efq
    3.30
     itſelf
    3.23
     Majefty
    3.16
     Monfieur
    3.13
     Jefus
    3.13
     Anſ
    3.11
     pleaſure
    3.06
     ―――――
    3.03
     purpoſe
    3.03
    Activations Density 0.671%

    No Known Activations