© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12378
    Prev
    Next
    INDEX
    Explanations

    language and structure commonly found in legal documents or court opinions

    oai_token-act-pair · gemini-2.0-flash

    general

    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
     profesión
    -0.53
    ConstraintMaker
    -0.51
     createSlice
    -0.51
     مشين
    -0.49
     significativos
    -0.49
    labilir
    -0.48
    Diwedd
    -0.48
    щадь
    -0.47
     Sinne
    -0.46
    setVerticalGroup
    -0.46
    POSITIVE LOGITS
     rule
    1.32
    rule
    1.09
     Rule
    0.99
     RULE
    0.98
    Rule
    0.87
     general
    0.79
     rules
    0.75
     getRule
    0.75
    RULE
    0.73
    general
    0.68
    Activations Density 2.369%

    No Known Activations