© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6995
    Prev
    Next
    INDEX
    Explanations

    latex code and document structure

    oai_token-act-pair · gemini-2.0-flash

    non-English terms or foreign language content

    np_token-act-pair-logits · gpt-4o-mini

    LaTeX documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Mémoire
    -0.57
    ずれ
    -0.54
     parlor
    -0.51
    ClassNotFound
    -0.50
    insegna
    -0.50
     sfera
    -0.49
    brania
    -0.49
    ();)
    -0.49
     catena
    -0.49
     Diener
    -0.48
    POSITIVE LOGITS
     tartalomajánló
    0.90
    Personensuche
    0.67
    ValueStyle
    0.66
    Népesség
    0.66
    Демографія
    0.64
    ंदीखरीदारी
    0.61
     Réponses
    0.60
     تضيفلها
    0.57
     oprot
    0.56
     مشين
    0.56
    Activations Density 5.110%

    No Known Activations