© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1959
    Prev
    Next
    INDEX
    Explanations

    mentions of sites and travel in Rome

    oai_token-act-pair · gemini-2.0-flash

    proper nouns related to landmarks and structures

    np_token-act-pair-logits · gpt-4o-mini

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     createSlice
    -0.57
    EndInit
    -0.54
    IGraphics
    -0.52
     resultCode
    -0.52
     onCancelled
    -0.49
    bukkit
    -0.48
    detectChanges
    -0.47
    fjspx
    -0.46
    "..."
    -0.46
    IntoConstraints
    -0.46
    POSITIVE LOGITS
     оригіналу
    0.70
     مشين
    0.69
     Coliseum
    0.63
     Co
    0.62
    loy
    0.61
     ISNI
    0.59
    كويكب
    0.59
     Eiffel
    0.57
     Rijks
    0.57
    Co
    0.56
    Activations Density 1.140%

    No Known Activations