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. 4-GEMMASCOPE-TRANSCODER-16K
    4. 7737
    Prev
    Next
    INDEX
    Explanations

    verbs, particularly those relating to offering/giving, receiving, or being in accordance with something.

    oai_token-act-pair · gemini-2.0-flash

    accusations or providing something

    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
     Ciencia
    -0.52
     scolaire
    -0.49
     institucional
    -0.48
     académico
    -0.47
    <bos>
    -0.47
     يتيمه
    -0.45
     Hobson
    -0.44
    ьаж
    -0.44
     directly
    -0.44
     étoit
    -0.44
    POSITIVE LOGITS
    >{@
    0.60
    رشف
    0.57
     BoxFit
    0.57
     cdti
    0.56
    AndEndTag
    0.56
    SerializedSize
    0.56
    URLException
    0.55
    تقاوى
    0.54
     ͡°
    0.53
    __":
    
    0.53
    Activations Density 1.595%

    No Known Activations