© 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. 9411
    Prev
    Next
    INDEX
    Explanations

    words related to business, real estate, and the law

    oai_token-act-pair · gemini-2.0-flash

    real estate

    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
    1
    -0.77
    3
    -0.66
    2
    -0.66
    4
    -0.65
    O
    -0.65
    5
    -0.64
    0
    -0.63
    7
    -0.63
    6
    -0.63
     @"/
    -0.62
    POSITIVE LOGITS
     Efq
    1.04
     Monfieur
    0.94
     myſelf
    0.93
     itſelf
    0.93
     Theſe
    0.86
     Cæsar
    0.86
     purpoſe
    0.84
     Jefus
    0.84
     Houſe
    0.84
     pleaſure
    0.84
    Activations Density 12.136%

    No Known Activations