© 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. 13344
    Prev
    Next
    INDEX
    Explanations

    technical documentation for video games

    oai_token-act-pair · gemini-2.0-flash

    Code/technical comments

    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
    adaptiveStyles
    -0.80
     quæ
    -0.77
     تضيفلها
    -0.73
     avoient
    -0.73
    Autoritní
    -0.72
     themſelves
    -0.70
    principalColumn
    -0.69
    GraphicsUnit
    -0.69
     enfans
    -0.69
     AssemblyCulture
    -0.68
    POSITIVE LOGITS
    ResumeLayout
    0.54
     imp
    0.51
     aegis
    0.50
     bastion
    0.50
    bral
    0.49
    loin
    0.48
    saraba
    0.47
    ring
    0.47
    val
    0.45
     ring
    0.45
    Activations Density 34.811%

    No Known Activations