© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6142
    Prev
    Next
    INDEX
    Explanations

    proper nouns and university titles

    oai_token-act-pair · gemini-2.0-flash

    awards/honors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    AndView
    -0.68
    SourceChecksum
    -0.67
    enumii
    -0.63
     AppModule
    -0.60
     rates
    -0.58
     الحره
    -0.58
     Rates
    -0.57
    
    -0.57
    consulté
    -0.57
     AssemblyVersion
    -0.57
    POSITIVE LOGITS
     Chair
    0.64
     End
    0.63
     ProtoMessage
    0.56
     memorial
    0.55
     Memorial
    0.55
    Chair
    0.54
     chair
    0.54
     Cup
    0.53
     end
    0.53
     Trophy
    0.53
    Activations Density 0.533%

    No Known Activations