© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 626
    Prev
    Next
    INDEX
    Explanations

    academic publications about optical physics or silicon.

    oai_token-act-pair · gemini-2.0-flash

    Scientific/technical writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    decin
    -0.49
    ضو
    -0.48
    mahal
    -0.47
    راسیون
    -0.45
     Malone
    -0.44
    ilon
    -0.42
     PROCEED
    -0.41
    esine
    -0.41
    maß
    -0.40
    ROUGH
    -0.40
    POSITIVE LOGITS
     Cæsar
    0.82
     Efq
    0.76
    yntaxException
    0.74
    ValueStyle
    0.73
     myſelf
    0.68
     himſelf
    0.68
     Theſe
    0.68
     Jefus
    0.66
    ":[{
    0.65
     LXXX
    0.65
    Activations Density 14.800%

    No Known Activations