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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 2301
    Prev
    Next
    INDEX
    Explanations

    the word "also" and other words that indicate something in addition to something else

    oai_token-act-pair · gemini-2.0-flash

    also

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    -1.02
     itſelf
    -1.01
    NUMX
    -1.01
     Theſe
    -0.99
     Efq
    -0.95
    ſhip
    -0.91
    '},
    
    -0.91
    AndEndTag
    -0.90
     ویکی‌پدیای
    -0.90
    `{.
    -0.90
    POSITIVE LOGITS
    ↵
    0.43
     ends
    0.40
     needs
    0.37
     performs
    0.37
    도
    0.36
      
    0.36
     üst
    0.35
     extends
    0.35
     pops
    0.35
    us
    0.35
    Activations Density 6.268%

    No Known Activations