© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6468
    Prev
    Next
    INDEX
    Explanations

    code snippets with square brackets and numbers, possibly array declarations or math functions

    oai_token-act-pair · gemini-2.0-flash

    Code and math symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     s
    -0.68
    -
    -0.67
    .
    -0.67
    (
    -0.66
     u
    -0.60
     a
    -0.60
    !
    -0.59
     di
    -0.58
    :
    -0.58
     den
    -0.56
    POSITIVE LOGITS
     Paglinawan
    1.09
     itſelf
    0.96
     Theſe
    0.91
     myſelf
    0.90
     autorytatywna
    0.89
     XNUMX
    0.87
     iſt
    0.86
     ་་
    0.85
    TemporalType
    0.85
     ―――――
    0.84
    Activations Density 4.003%

    No Known Activations