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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 6891
    Prev
    Next
    INDEX
    Explanations

    the word "however" plus commas and some words such as "there" and "in."

    oai_token-act-pair · gemini-2.0-flash

    comma

    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
    ⓧ
    -1.45
     Efq
    -1.22
    Personendaten
    -1.20
     незавершена
    -1.19
     Majefty
    -1.11
    رشف
    -1.09
    WithIOException
    -1.07
    GEBURTSDATUM
    -1.07
    ſelf
    -1.05
    IsMutable
    -1.04
    POSITIVE LOGITS
     
    1.07
    ↵↵
    1.00
    ↵
    0.91
    .
    0.87
     The
    0.85
     In
    0.85
     that
    0.85
    The
    0.83
    In
    0.82
    '
    0.78
    Activations Density 1.995%

    No Known Activations