© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10613
    Prev
    Next
    INDEX
    Explanations

    text from internet chat rooms, possibly in multiple languages, containing conversational filler words, questions, and code snippets.

    oai_token-act-pair · gemini-2.0-flash

    non-english text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     well
    -0.53
     rest
    -0.50
     men
    -0.49
     to
    -0.47
     help
    -0.46
     left
    -0.46
     un
    -0.45
     on
    -0.45
     import
    -0.44
     up
    -0.44
    POSITIVE LOGITS
     anún
    0.76
     financières
    0.75
     juridiques
    0.74
     refroid
    0.73
     nahilalakip
    0.71
     mères
    0.71
     démocr
    0.69
     pouvoit
    0.69
     prochaines
    0.68
    
    0.68
    Activations Density 7.276%

    No Known Activations