© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5552
    Prev
    Next
    INDEX
    Explanations

    words related to the quantity or measurement of things, sometimes in a scientific context

    oai_token-act-pair · gemini-2.0-flash

    prepositions or linking words

    np_token-act-pair-logits · gpt-4o-mini

    numerical changes and amounts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    MigrationBuilder
    -0.71
    uisine
    -0.63
    .*")]
    -0.53
    akyti
    -0.48
     /(\
    -0.47
    󠁢
    -0.46
     <>",
    -0.46
     PeEnEo
    -0.46
    Personensuche
    -0.45
     föruts
    -0.45
    POSITIVE LOGITS
     in
    1.88
     dalam
    0.90
     في
    0.85
    ใน
    0.84
    MemoryWarning
    0.83
     в
    0.81
     în
    0.79
    Dalam
    0.76
    dalam
    0.75
     σε
    0.73
    Activations Density 2.124%

    No Known Activations