© 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. 12916
    Prev
    Next
    INDEX
    Explanations

    LaTeX code

    oai_token-act-pair · gemini-2.0-flash

    LaTeX and 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
     sportiva
    -0.50
    odas
    -0.50
    nyx
    -0.49
     SEDS
    -0.49
     deportiva
    -0.47
     ALR
    -0.47
    zzar
    -0.46
     snoring
    -0.46
     Siren
    -0.45
     sobs
    -0.44
    POSITIVE LOGITS
     $]$
    0.73
    LikeLike
    0.70
    )−
    0.67
    endwhile
    0.67
    — 
    0.67
    /−
    0.66
    )$\\
    0.66
    ']))
    0.64
    ''')
    0.64
    """)
    0.64
    Activations Density 4.309%

    No Known Activations