© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10136
    Prev
    Next
    INDEX
    Explanations

    abbreviated or incomplete information

    oai_token-act-pair · gemini-2.0-flash

    health and medicine

    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
     …
    -1.31
     ...
    -0.96
     
    -0.83
     […]
    -0.77
     I
    -0.71
     …”
    -0.70
     U
    -0.69
     very
    -0.69
     A
    -0.68
    <eos>
    -0.66
    POSITIVE LOGITS
     ainfi
    1.20
     Theſe
    1.14
     Monfieur
    1.07
     auffi
    1.01
     itſelf
    1.00
     myſelf
    0.99
     asiatique
    0.98
     Cæsar
    0.97
     pouvoit
    0.96
     Jefus
    0.95
    Activations Density 0.980%

    No Known Activations