© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3826
    Prev
    Next
    INDEX
    Explanations

    multiple references to locations and people in China including Chinese characters

    oai_token-act-pair · gemini-2.0-flash

    (

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     propOrder
    -0.75
    <bos>
    -0.71
     مشين
    -0.68
    .*")]
    -0.67
    )++;
    -0.65
    DeleteBehavior
    -0.65
    __;
    -0.65
     MainAxisSize
    -0.65
    WithIOException
    -0.64
    enumi
    -0.63
    POSITIVE LOGITS
     enfans
    0.40
     publiques
    0.39
     desar
    0.36
     hals
    0.34
     gagné
    0.33
     bílá
    0.33
    mű
    0.32
     domestiques
    0.31
     sauvages
    0.31
    lardır
    0.31
    Activations Density 0.183%

    No Known Activations