© 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. 12435
    Prev
    Next
    INDEX
    Explanations

    line numbers in file paths or number sequences

    oai_token-act-pair · gemini-2.0-flash

    Code and data

    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
     nine
    -0.63
     seven
    -0.61
     five
    -0.57
     four
    -0.57
     six
    -0.56
     two
    -0.56
     three
    -0.54
     eight
    -0.52
    getReference
    -0.49
     v
    -0.48
    POSITIVE LOGITS
     سكانية
    0.71
     Theſe
    0.64
    DockStyle
    0.63
    ̍t
    0.61
     utafitiHapana
    0.58
    __":
    0.55
    BeginContext
    0.53
     Vikipedi
    0.52
     doméstica
    0.52
    ThroughAttribute
    0.52
    Activations Density 5.891%

    No Known Activations