© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5530
    Prev
    Next
    INDEX
    Explanations

    the code variable named "obj"

    oai_token-act-pair · gemini-2.0-flash

    obj

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     
    -1.41
     “
    -1.02
     a
    -1.01
     "
    -0.95
      
    -0.93
     the
    -0.91
     ‘
    -0.88
     an
    -0.84
     '
    -0.81
     so
    -0.81
    POSITIVE LOGITS
     itſelf
    1.63
     iſt
    1.53
     ſtate
    1.50
     Monfieur
    1.45
     Efq
    1.44
     Reſ
    1.42
     myſelf
    1.42
     auffi
    1.42
     ſche
    1.40
     pleaſure
    1.40
    Activations Density 4.116%

    No Known Activations