© 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. 4185
    Prev
    Next
    INDEX
    Explanations

    code snippets involving file paths and directory manipulation

    oai_token-act-pair · gemini-2.0-flash

    code/file paths

    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
     dir
    -0.58
    dir
    -0.57
    Dirs
    -0.49
     file
    -0.48
    Dir
    -0.47
     directores
    -0.46
     lentil
    -0.45
     onOptions
    -0.45
    Midnight
    -0.44
     directory
    -0.44
    POSITIVE LOGITS
    Билгалдахарш
    0.75
     propOrder
    0.73
    :✨
    0.68
    MigrationBuilder
    0.63
    ViewFeatures
    0.62
     familières
    0.60
    Composable
    0.59
     chắn
    0.59
    rungsseite
    0.56
    enity
    0.54
    Activations Density 1.297%

    No Known Activations