© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 5642
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions, code, and citations.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    StructEnd
    -0.65
     betweenstory
    -0.63
    
    -0.54
    BeginContext
    -0.49
    انيف
    -0.47
    ViewFeatures
    -0.46
    bcryptjs
    -0.45
     <>",
    -0.45
     joaat
    -0.44
     resourceCulture
    -0.44
    POSITIVE LOGITS
    OF
    0.75
     ofthe
    0.68
    यह
    0.66
    Le
    0.65
    और
    0.65
    HAS
    0.64
     OF
    0.62
    PUR
    0.61
    Bạn
    0.59
    LE
    0.58
    Activations Density 13.905%

    No Known Activations