© 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
    2. Gemma-2-2B
    3. 3-GEMMASCOPE-TRANSCODER-16K
    4. 9264
    Prev
    Next
    INDEX
    Explanations

    pronouns and prepositional phrases in multiple languages

    oai_token-act-pair · gemini-2.0-flash

    online conversations, legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    <bos>
    -1.07
     there
    -0.82
    there
    -0.67
    abetes
    -0.66
    AndEndTag
    -0.65
    看来
    -0.61
    PropertyGroup
    -0.57
    Geplaatst
    -0.57
    StructEnd
    -0.56
     they
    -0.56
    POSITIVE LOGITS
    avy
    0.55
    (&_
    0.52
    --){
    0.52
    izou
    0.52
    alamy
    0.52
    hada
    0.51
    '):
    
    0.51
    ITTLE
    0.50
    ']==
    0.50
    patent
    0.50
    Activations Density 1.714%

    No Known Activations