© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 3788
    Prev
    Next
    INDEX
    Explanations

    java code and documentation related to it

    oai_token-act-pair · gemini-2.0-flash

    Java code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     forming
    -1.09
     compose
    -1.06
     comprise
    -0.96
     constituting
    -0.95
     Forming
    -0.93
     comprising
    -0.92
     composing
    -0.87
     constitute
    -0.86
     membentuk
    -0.86
    forming
    -0.84
    POSITIVE LOGITS
    '])->
    0.65
    ########.
    0.61
     auroit
    0.60
    ')):
    0.60
     avoient
    0.59
     définiti
    0.59
    ValueStyle
    0.59
    initely
    0.58
    ."</
    0.58
     étoit
    0.56
    Activations Density 1.006%

    No Known Activations