© 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. 14127
    Prev
    Next
    INDEX
    Explanations

    single-letter capitalized initials, possibly for author names in scientific publications

    oai_token-act-pair · gemini-2.0-flash

    A or E

    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
     
    -0.56
     “
    -0.54
     total
    -0.53
     Man
    -0.52
     \#
    -0.51
     ‘
    -0.50
     La
    -0.49
    usi
    -0.49
    tog
    -0.49
     patter
    -0.49
    POSITIVE LOGITS
    ⓧ
    0.84
    SharedDtor
    0.80
     kasarigan
    0.78
     nakalista
    0.77
    Geplaatst
    0.73
    parsedMessage
    0.70
     consultato
    0.68
     препратки
    0.68
     GenerationType
    0.67
     surla
    0.67
    Activations Density 0.956%

    No Known Activations