© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10150
    Prev
    Next
    INDEX
    Explanations

    mentions of regions of the brain.

    oai_token-act-pair · gemini-2.0-flash

    brain regions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    AccessorTable
    -0.61
    UseVisualStyle
    -0.57
    OrNil
    -0.54
     propOrder
    -0.53
    InSection
    -0.52
    parsedMessage
    -0.51
    newswire
    -0.50
    ImageContext
    -0.49
     Blanca
    -0.49
     صوتيه
    -0.48
    POSITIVE LOGITS
     мѣ
    0.58
     Италијани
    0.57
    ViewFeatures
    0.54
    batore
    0.54
     InputDecoration
    0.53
     faptul
    0.52
     لئے
    0.50
    hova
    0.49
    iddish
    0.48
    MENAFN
    0.47
    Activations Density 1.898%

    No Known Activations