© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15515
    Prev
    Next
    INDEX
    Explanations

    angle brackets, dollar signs, and other characters commonly used in programming code

    oai_token-act-pair · 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
     feroit
    -0.83
     auroit
    -0.82
     pouvoit
    -0.80
     avoient
    -0.80
     étoient
    -0.79
     mauva
    -0.78
     étoit
    -0.77
     Efq
    -0.76
     neutre
    -0.75
     aveug
    -0.74
    POSITIVE LOGITS
    應該
    0.36
    â
    0.35
    itinéraire
    0.35
    請
    0.34
    ”.
    0.34
    時
    0.34
    設定
    0.33
     時
    0.33
     And
    0.33
    ’.
    0.33
    Activations Density 9.741%

    No Known Activations