© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10452
    Prev
    Next
    INDEX
    Explanations

    articles, prepositions, and numbers within sports articles

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    SourceChecksum
    -0.57
    StructEnd
    -0.56
    ViewImports
    -0.53
      
    -0.53
    }]);
    -0.51
     épic
    -0.51
     jouets
    -0.51
    manta
    -0.50
     '\\;'
    -0.50
     betweenstory
    -0.50
    POSITIVE LOGITS
    Pemer
    0.57
     governorship
    0.53
     springfox
    0.51
    <?
    0.49
    arctan
    0.49
     XCTest
    0.48
    AndroidJUnit
    0.48
     PTS
    0.47
    
    0.47
    Géographie
    0.47
    Activations Density 0.551%

    No Known Activations