© 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. 6782
    Prev
    Next
    INDEX
    Explanations

    what appears to be code and punctuation used in programming

    oai_token-act-pair · gemini-2.0-flash

    Facebook account verification strings

    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
    antes
    -0.36
    MemoryWarning
    -0.32
    Just
    -0.32
     연
    -0.32
     disser
    -0.31
    ưởng
    -0.31
     Guarda
    -0.31
    ggi
    -0.30
    protoimpl
    -0.30
     g
    -0.29
    POSITIVE LOGITS
    ValueStyle
    0.75
     itſelf
    0.74
     للمعارف
    0.73
     Савезне
    0.73
     Wikimedijinoj
    0.70
     myſelf
    0.69
    BufferException
    0.67
    ConstraintMaker
    0.67
     contextLoads
    0.66
    ifoli
    0.66
    Activations Density 0.740%

    No Known Activations