© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11126
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to how-to guides, advice, and recommendations

    oai_token-act-pair · 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
     yours
    -1.06
     sua
    -1.04
     tu
    -1.03
     seu
    -0.98
    Tu
    -0.97
     my
    -0.96
     Their
    -0.93
    Their
    -0.93
     suas
    -0.91
     seus
    -0.90
    POSITIVE LOGITS
     InputDecoration
    0.52
    stdc
    0.50
    argout
    0.49
    medriver
    0.47
    bitField
    0.45
    tonsoft
    0.45
    [:,:,
    0.45
    dez
    0.45
    ophi
    0.45
    stead
    0.45
    Activations Density 3.087%

    No Known Activations