© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12582
    Prev
    Next
    INDEX
    Explanations

    terms describing the structure, function and study of neurons in the cortex

    oai_token-act-pair · gemini-2.0-flash

    the and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     EconPapers
    -0.61
     HasFactory
    -0.57
     siihen
    -0.56
     Bex
    -0.53
     commitments
    -0.50
    الخ
    -0.48
     Cæsar
    -0.48
     Coder
    -0.48
    ;#
    -0.48
     enchantment
    -0.48
    POSITIVE LOGITS
     /\.
    0.57
     /\.(
    0.57
    Personendaten
    0.52
    DropTable
    0.50
    DropColumn
    0.50
    ManagedBean
    0.49
     betweenstory
    0.49
    EndGlobalSection
    0.48
     dAtA
    0.48
     autorytatywna
    0.48
    Activations Density 2.235%

    No Known Activations