© 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. 7561
    Prev
    Next
    INDEX
    Explanations

    lines in a computer program that have a bracket on them

    oai_token-act-pair · gemini-2.0-flash

    Code abbreviations

    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
     Efq
    -1.11
     avoient
    -1.09
     étoient
    -1.01
     myſelf
    -1.01
     étoit
    -1.01
     iſt
    -0.98
     habet
    -0.98
     auroit
    -0.98
     Jefus
    -0.97
     ainfi
    -0.97
    POSITIVE LOGITS
    ↵↵
    0.75
    <eos>
    0.73
    SequentialGroup
    0.68
    ↵
    0.66
    </b>
    0.65
     F
    0.63
     f
    0.63
     N
    0.63
     D
    0.62
    D
    0.62
    Activations Density 2.215%

    No Known Activations