© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7243
    Prev
    Next
    INDEX
    Explanations

    source code or phone numbers

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    -2.55
     myſelf
    -2.47
     Majefty
    -2.38
     $_"
    -2.38
    ^(@)
    -2.38
    ſelf
    -2.33
     itſelf
    -2.31
     Monfieur
    -2.28
     Jefus
    -2.27
     themſelves
    -2.25
    POSITIVE LOGITS
    -
    1.54
    ↵
    1.51
     
    1.48
    ,
    1.45
    .
    1.42
     (
    1.38
    ↵↵
    1.34
    :
    1.24
      
    1.24
    <eos>
    1.23
    Activations Density 3.513%

    No Known Activations