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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7001
    Prev
    Next
    INDEX
    Explanations

    words indicating small amounts or degrees, often used to soften statements

    oai_token-act-pair · gemini-2.0-flash

    lab

    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
    ſelf
    -0.97
     myſelf
    -0.94
    LLocation
    -0.93
     themſelves
    -0.91
     Efq
    -0.90
    úrese
    -0.88
     ―――――
    -0.87
     Anſ
    -0.84
    KommentareTeilen
    -0.84
    themselves
    -0.84
    POSITIVE LOGITS
     a
    0.90
     another
    0.71
     sebuah
    0.69
     an
    0.69
     μια
    0.66
     isang
    0.57
     one
    0.54
     chiếc
    0.54
     liten
    0.52
     A
    0.51
    Activations Density 1.852%

    No Known Activations