© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 6420
    Prev
    Next
    INDEX
    Explanations

    quantities, especially those related to finance

    oai_token-act-pair · gemini-2.0-flash

    Numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     resourceCulture
    -0.91
     SafeMath
    -0.78
    interopRequire
    -0.76
     ujednoznacz
    -0.75
    ILayout
    -0.73
     MatDialog
    -0.72
    nsics
    -0.71
    CodedInputStream
    -0.70
    ⓧ
    -0.69
    ViewImports
    -0.68
    POSITIVE LOGITS
     about
    0.57
     $
    0.53
    0
    0.48
    5
    0.47
    1
    0.47
    6
    0.43
    4
    0.42
    3
    0.42
    7
    0.42
    8
    0.42
    Activations Density 15.294%

    No Known Activations