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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14897
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a good time to do something

    oai_token-act-pair · gemini-2.0-flash

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    تقاوى
    -0.61
    ]--;
    -0.60
     للاسماء
    -0.59
    toHaveBeenCalled
    -0.57
    KommentareTeilen
    -0.56
    VersionUID
    -0.56
     متعلقه
    -0.55
     ModelExpression
    -0.54
     onResponse
    -0.52
    JNIEnv
    -0.52
    POSITIVE LOGITS
     is
    2.38
     isn
    1.27
     was
    1.20
     adalah
    1.12
     Is
    1.09
     isnt
    1.00
     είναι
    1.00
     là
    0.99
    is
    0.94
     IS
    0.94
    Activations Density 1.487%

    No Known Activations