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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14137
    Prev
    Next
    INDEX
    Explanations

    words or phrases that introduce additional information or worsen a situation

    oai_token-act-pair · gemini-2.0-flash

    Increase or worsening

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ddot
    -0.45
     eigentlich
    -0.43
     Camargo
    -0.43
     totales
    -0.43
     wohl
    -0.43
    imetsu
    -0.41
     dags
    -0.40
     aéro
    -0.40
    möglichkeiten
    -0.39
    لي
    -0.39
    POSITIVE LOGITS
     dessutom
    0.88
     navíc
    0.81
    TagMode
    0.79
     moreover
    0.77
    addCriterion
    0.75
    addition
    0.75
     Inoltre
    0.73
     additionally
    0.73
    AndEndTag
    0.73
    principalColumn
    0.72
    Activations Density 1.259%

    No Known Activations