© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12408
    Prev
    Next
    INDEX
    Explanations

    words related to the brain, nervous system, and neuroscience research.

    oai_token-act-pair · gemini-2.0-flash

    Synapses

    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
     démission
    -0.48
    
    -0.46
    chossen
    -0.41
    bootstrapcdn
    -0.41
     meur
    -0.40
     aveug
    -0.40
     religieuses
    -0.40
     chré
    -0.40
    atchewan
    -0.40
    Koordinaten
    -0.40
    POSITIVE LOGITS
     RP
    1.20
     CP
    1.18
     TP
    1.16
     dp
    1.15
     rp
    1.14
     jp
    1.14
     cp
    1.13
     lp
    1.10
     FP
    1.09
    tp
    1.08
    Activations Density 7.367%

    No Known Activations