© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14682
    Prev
    Next
    INDEX
    Explanations

    code syntax and mathematical inequalities, particularly parentheses, brackets, and quotes, but also some contractions like "isn't"

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
     Cæsar
    -0.42
     Pues
    -0.33
     Sopho
    -0.32
     Phry
    -0.30
     Thebes
    -0.30
     Thine
    -0.29
     hierogly
    -0.29
     Tacitus
    -0.29
     Oedipus
    -0.29
     Nadie
    -0.28
    POSITIVE LOGITS
     stället
    0.74
     fermés
    0.72
     réfrig
    0.70
     jouets
    0.69
     déchir
    0.68
     âmes
    0.68
     pouvoirs
    0.68
     détru
    0.68
     supérieurs
    0.68
     rêves
    0.68
    Activations Density 1.338%

    No Known Activations