© 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. 10158
    Prev
    Next
    INDEX
    Explanations

    phrases describing alerts, accusations, problems, or formal language

    oai_token-act-pair · gemini-2.0-flash

    conflict

    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
     attacks
    -1.19
     assaults
    -1.10
     visits
    -1.06
     Attacks
    -1.06
    Attacks
    -1.02
     searches
    -1.01
     fights
    -0.99
     robberies
    -0.99
     defeats
    -0.98
    attacks
    -0.97
    POSITIVE LOGITS
     تانيه
    0.65
     unknownFields
    0.65
     розви
    0.63
    مصادر
    0.62
    istice
    0.61
    
    0.59
    PyExc
    0.58
    endphp
    0.57
    IntoConstraints
    0.57
    λικά
    0.56
    Activations Density 10.351%

    No Known Activations