© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8185
    Prev
    Next
    INDEX
    Explanations

    capital letters used in programming code

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     ſche
    -1.17
     Efq
    -1.09
     purpoſe
    -1.02
     myſelf
    -1.02
     Jefus
    -1.01
     Anſ
    -1.01
     Chriftian
    -1.00
     ſtate
    -0.98
     iſt
    -0.96
     fevere
    -0.96
    POSITIVE LOGITS
     d
    0.70
     l
    0.68
     p
    0.66
     som
    0.65
     i
    0.64
     f
    0.64
     tre
    0.63
     so
    0.61
     m
    0.60
     my
    0.60
    Activations Density 1.175%

    No Known Activations