© 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. 1151
    Prev
    Next
    INDEX
    Explanations

    references to academic publications, including citations and journal titles

    oai_token-act-pair · gemini-2.0-flash

    Academic citations

    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
     Garrett
    -0.39
     Marcus
    -0.39
    frontmatter
    -0.39
     Vincent
    -0.38
     Martin
    -0.38
     Graham
    -0.38
    laine
    -0.38
     Gordon
    -0.38
     Maximus
    -0.37
     Rose
    -0.37
    POSITIVE LOGITS
    \}\\
    0.71
    存于互联网档案馆
    0.70
    IntoConstraints
    0.65
     للاسماء
    0.64
    SourceChecksum
    0.63
     (
    0.59
    StoryboardSegue
    0.58
      
    0.58
    AutoresizingMask
    0.56
    '])
    0.55
    Activations Density 14.531%

    No Known Activations