Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 14481
    Prev
    Next
    INDEX
    Explanations

    the word "to" and words that commonly occur near it or other short common words

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    -1.04
     Jefus
    -0.99
     itſelf
    -0.90
     Efq
    -0.86
     Cæsar
    -0.86
     himſelf
    -0.84
     themſelves
    -0.84
    ^(@)
    -0.84
     theſe
    -0.83
    ſelves
    -0.83
    POSITIVE LOGITS
     
    0.61
     an
    0.42
    ark
    0.37
    ViewChild
    0.37
     å
    0.36
     a
    0.35
     twenty
    0.35
     $
    0.34
    readystatechange
    0.32
     thirty
    0.32
    Activations Density 6.261%

    No Known Activations