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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 16271
    Prev
    Next
    INDEX
    Explanations

    references to legal documents and legal terms in a written legal argument

    oai_token-act-pair · gemini-2.0-flash

    Legal cases and code

    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
     plă
    -0.46
     necesar
    -0.45
     gând
    -0.45
     blanche
    -0.42
     fubject
    -0.40
     atât
    -0.40
     članak
    -0.40
     alimentaria
    -0.40
     šķ
    -0.40
     terza
    -0.39
    POSITIVE LOGITS
    principalColumn
    0.93
     cref
    0.93
    NUMX
    0.90
    9
    0.88
    1
    0.86
    8
    0.77
    7
    0.74
    sizeCache
    0.73
    6
    0.73
     الاطلاع
    0.71
    Activations Density 36.288%

    No Known Activations