© 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. 11256
    Prev
    Next
    INDEX
    Explanations

    This neuron seems to activate on words related to scientific research in various fields.

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    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
    -2.20
     pro
    -2.16
    Pro
    -2.06
     PRO
    -2.05
    pro
    -1.95
    PRO
    -1.89
     Pros
    -1.82
     Prop
    -1.79
     pros
    -1.65
     prop
    -1.64
    POSITIVE LOGITS
     estekak
    0.60
     متعلقه
    0.58
     battre
    0.56
     camicia
    0.53
    hoeddwyd
    0.51
    Kilder
    0.50
     murale
    0.47
     colorés
    0.47
     devenus
    0.46
     librement
    0.45
    Activations Density 1.470%

    No Known Activations