© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10038
    Prev
    Next
    INDEX
    Explanations

    legal documents and formal language

    oai_token-act-pair · gemini-2.0-flash

    Legal 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_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     <=",
    -0.70
    hyrchwyd
    -0.67
     ویکی‌پدیا
    -0.65
    fjspx
    -0.65
    PhysRevLett
    -0.63
     unknownFields
    -0.61
    RegistryLite
    -0.61
    AndroidJUnit
    -0.61
     houſe
    -0.61
    ValueStyle
    -0.60
    POSITIVE LOGITS
     кой
    0.47
    öffentlichungen
    0.46
     ostavi
    0.45
     án
    0.44
    }`)
    0.43
    Спасылкі
    0.43
    }}"
    0.42
    ociação
    0.41
    "],
    0.41
     end
    0.40
    Activations Density 0.278%

    No Known Activations