© 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. 12440
    Prev
    Next
    INDEX
    Explanations

    words and phrases about navigating and using software, especially for coding

    oai_token-act-pair · gemini-2.0-flash

    UI elements

    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
    writeFieldEnd
    -0.73
    ftagPool
    -0.66
    StoryboardSegue
    -0.61
    MigrationBuilder
    -0.60
    MeasureSpec
    -0.58
    PRNewswire
    -0.57
     Carthag
    -0.55
     vej
    -0.55
    jewództ
    -0.54
     BIBSYS
    -0.53
    POSITIVE LOGITS
     on
    0.64
     in
    0.58
     next
    0.53
     above
    0.50
     to
    0.50
     références
    0.48
    bove
    0.46
    Literatuur
    0.45
     behind
    0.45
    startswith
    0.44
    Activations Density 12.892%

    No Known Activations