© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5133
    Prev
    Next
    INDEX
    Explanations

    clauses about whether something is intended or not

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    ніципалі
    -0.62
    ALAM
    -0.62
     Fais
    -0.57
    Népesség
    -0.57
     curi
    -0.51
    Chham
    -0.51
     Baile
    -0.50
    ddin
    -0.50
    jala
    -0.50
     незавершена
    -0.49
    POSITIVE LOGITS
     intended
    1.98
    intended
    1.77
     Intended
    1.65
     designed
    1.60
    Intended
    1.45
    designed
    1.39
     intention
    1.37
     intent
    1.35
     Designed
    1.34
     design
    1.34
    Activations Density 1.485%

    No Known Activations