© 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. 13866
    Prev
    Next
    INDEX
    Explanations

    words that appear in formal writing and instructions

    oai_token-act-pair · gemini-2.0-flash

    comments

    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
     conducted
    -1.36
     executed
    -1.32
     Performed
    -1.30
    conducted
    -1.29
    taken
    -1.27
     performed
    -1.27
     Conducted
    -1.26
    executed
    -1.25
     undertaken
    -1.25
     released
    -1.25
    POSITIVE LOGITS
    ')")
    0.56
    })));
    0.50
    dientemente
    0.46
    ylvan
    0.46
     []),
    0.44
     {}),
    0.41
    vení
    0.40
     />,
    0.40
     Munt
    0.40
    offsetof
    0.40
    Activations Density 3.008%

    No Known Activations