© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5719
    Prev
    Next
    INDEX
    Explanations

    a variety of short conjunctions, mathematical formulas, and conversational filler

    oai_token-act-pair · gemini-2.0-flash

    mathematical expressions

    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
     providing
    -1.53
     provide
    -1.51
     provided
    -1.48
     Providing
    -1.45
    Providing
    -1.44
     Provide
    -1.42
    provided
    -1.40
    providing
    -1.40
    provide
    -1.39
     Giving
    -1.38
    POSITIVE LOGITS
     G
    0.76
    G
    0.63
    apimachinery
    0.61
    TestBed
    0.59
     Gw
    0.56
     g
    0.54
    VolleyError
    0.53
    strptime
    0.49
    sizeCache
    0.48
     Competi
    0.47
    Activations Density 2.503%

    No Known Activations