© 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. 4053
    Prev
    Next
    INDEX
    Explanations

    mathematical word problems

    oai_token-act-pair · gemini-2.0-flash

    Math/programming calculations

    np_max-act-logits · 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
     autorytatywna
    -0.90
    -------------</
    -0.77
    хьтан
    -0.66
     Administrativna
    -0.63
    PreferredItem
    -0.60
    Rhestr
    -0.59
     postIndex
    -0.58
     kasarigan
    -0.58
     BoxDecoration
    -0.57
    rippa
    -0.57
    POSITIVE LOGITS
     ☺
    0.52
     Numerical
    0.50
     Exercises
    0.49
     Sketch
    0.49
     numerically
    0.48
    EZ
    0.48
     bağlantılar
    0.45
    inac
    0.45
     approximation
    0.44
    XT
    0.44
    Activations Density 16.125%

    No Known Activations