© 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. 7870
    Prev
    Next
    INDEX
    Explanations

    references to figures and equations, especially in a mathematical or technical context

    oai_token-act-pair · gemini-2.0-flash

    math and science

    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
     Delta
    -1.97
     Alpha
    -1.79
     delta
    -1.77
     Beta
    -1.71
     alpha
    -1.70
     DELTA
    -1.68
     Gamma
    -1.65
     Omega
    -1.62
     beta
    -1.61
    Delta
    -1.60
    POSITIVE LOGITS
     ligiloj
    0.59
    StoryboardSegue
    0.52
    CONV
    0.51
    migrationBuilder
    0.50
     Carrick
    0.49
    AsStream
    0.47
     дописавши
    0.46
     εικό
    0.46
     gyhoeddwyd
    0.45
    __":
    
    0.45
    Activations Density 2.715%

    No Known Activations