© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5390
    Prev
    Next
    INDEX
    Explanations

    relationships between numbers, dates, statistical findings, and research

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Pro
    -0.80
     Meta
    -0.69
    Pro
    -0.67
     Con
    -0.64
     Mod
    -0.63
     Ex
    -0.61
     Sem
    -0.60
     Auto
    -0.60
     Res
    -0.60
     Per
    -0.60
    POSITIVE LOGITS
     Monfieur
    1.20
     ainfi
    1.18
     Houſe
    1.13
     purpoſe
    1.11
    ſelf
    1.09
     auffi
    1.08
     Jefus
    1.05
     houſe
    1.05
     faſt
    1.05
     myſelf
    1.04
    Activations Density 26.315%

    No Known Activations