© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2858
    Prev
    Next
    INDEX
    Explanations

    code snippets and syntax from programming languages.

    oai_token-act-pair · gemini-2.0-flash

    say "="

    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
    Negative Logits
     CreateTagHelper
    -1.16
     propOrder
    -1.13
    StoryboardSegue
    -1.12
    Personendaten
    -1.10
     AssemblyCulture
    -1.09
     EconPapers
    -1.09
    CloseOperation
    -1.07
    ]")]
    -1.06
     Paglinawan
    -1.03
    +#+
    -1.02
    POSITIVE LOGITS
     =
    0.69
     
    0.55
    <strong>
    0.49
    check
    0.49
    .
    0.49
    Op
    0.48
    une
    0.47
    len
    0.46
    4
    0.46
     //
    0.45
    Activations Density 6.135%

    No Known Activations