© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15484
    Prev
    Next
    INDEX
    Explanations

    terms related to legal proceedings, especially testimony and examination

    oai_token-act-pair · gemini-2.0-flash

    argument examination

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    cyklopedia
    -0.88
     '\\;'
    -0.88
     nahilalakip
    -0.83
     Infórmanos
    -0.82
     समीक्षाओं
    -0.78
     Мексичка
    -0.77
    NUMX
    -0.75
     InputDecoration
    -0.75
    HasAnnotation
    -0.75
    ViewFeatures
    -0.75
    POSITIVE LOGITS
    .
    0.44
     it
    0.44
    co
    0.42
    ↵
    0.40
     daran
    0.40
    @
    0.40
    InlineData
    0.38
    jit
    0.38
     szab
    0.37
     our
    0.37
    Activations Density 2.192%

    No Known Activations