© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15176
    Prev
    Next
    INDEX
    Explanations

    words or symbols commonly used in scientific or mathematical papers, including descriptions of study parameters and statistical analyses.

    oai_token-act-pair · gemini-2.0-flash

    into

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    andExpect
    -0.81
     doInBackground
    -0.71
     المعيارى
    -0.60
    ftagPool
    -0.59
     nahilalakip
    -0.59
    COUVER
    -0.57
    Jîn
    -0.56
    
    -0.55
     noten
    -0.55
     ErrIntOverflow
    -0.55
    POSITIVE LOGITS
     незавершена
    0.53
    ന്ന്
    0.52
    (!__
    0.48
     hain
    0.46
    Халык
    0.46
     Hesse
    0.46
    msubsup
    0.45
    ENSIONS
    0.45
    GoogleApiClient
    0.45
     precedente
    0.43
    Activations Density 62.019%

    No Known Activations