© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7693
    Prev
    Next
    INDEX
    Explanations

    javascript code snippets dealing with chart area height and width

    oai_token-act-pair · gemini-2.0-flash

    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_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
    3
    -0.86
    2
    -0.82
    0
    -0.59
    makeText
    -0.54
     newOwner
    -0.46
    8
    -0.46
    9
    -0.42
     three
    -0.42
    ficulty
    -0.40
    1
    -0.40
    POSITIVE LOGITS
    esez
    0.85
    writeFieldEnd
    0.68
    Enllaços
    0.68
    ⓧ
    0.66
     cherchés
    0.66
     EconPapers
    0.66
     pinulongan
    0.65
     ***!
    0.64
    Spoljašnje
    0.64
     فريبيس
    0.62
    Activations Density 0.534%

    No Known Activations