© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10427
    Prev
    Next
    INDEX
    Explanations

    film review article metadata and related movie opinions.

    oai_token-act-pair · gemini-2.0-flash

    French vocabulary terms

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

    period

    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
    
    -0.49
    Externe
    -0.47
     meh
    -0.47
     חיצוניים
    -0.46
     <<<<<<<<<<<<<<
    -0.44
     smtplib
    -0.43
    ρίες
    -0.40
     Meh
    -0.40
    alité
    -0.40
     sessionFactory
    -0.40
    POSITIVE LOGITS
     jouets
    0.75
     épaules
    0.69
     vectoriales
    0.69
    Cordialement
    0.68
     pacchetto
    0.68
    RenderAtEndOf
    0.67
     collègues
    0.65
     colonnes
    0.65
    GTCX
    0.65
     fourrure
    0.64
    Activations Density 1.711%

    No Known Activations