© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12928
    Prev
    Next
    INDEX
    Explanations

    fragments of words of unknown origin, possibly related to code or medical terms

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     تضيفلها
    -0.73
     lenker
    -0.65
    
    -0.63
    Geplaatst
    -0.59
    esgue
    -0.57
    JvmStatic
    -0.50
    المناصب
    -0.50
    Brainz
    -0.49
    AsUp
    -0.49
    PerformLayout
    -0.48
    POSITIVE LOGITS
    se
    0.92
    si
    0.77
    sev
    0.71
    sela
    0.68
    sew
    0.68
    sem
    0.67
    sea
    0.67
    sef
    0.66
    sel
    0.63
    seb
    0.63
    Activations Density 2.374%

    No Known Activations