© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12788
    Prev
    Next
    INDEX
    Explanations

    concepts related to goals, opinions, importance, challenges, and societal constructs

    oai_token-act-pair · gemini-2.0-flash

    Encoding issues

    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
     Efq
    -1.16
    ſelf
    -1.12
     Monfieur
    -1.04
     myſelf
    -1.03
     Majefty
    -1.01
     onOptions
    -0.99
    ſelves
    -0.99
    neſs
    -0.97
     Houſe
    -0.97
     itſelf
    -0.97
    POSITIVE LOGITS
     â
    0.84
    â
    0.82
     �
    0.77
    �
    0.76
     ?
    0.74
     _
    0.71
      
    0.71
     -
    0.63
    &#
    0.58
     &#
    0.58
    Activations Density 2.135%

    No Known Activations