© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5372
    Prev
    Next
    INDEX
    Explanations

    references to the Quran

    oai_token-act-pair · gemini-2.0-flash

    Cal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     gynhyrchwyd
    -0.79
     kasarigan
    -0.79
    ">//
    -0.76
    
    -0.71
     GenerationType
    -0.70
     ExecuteAsync
    -0.70
    IntoConstraints
    -0.69
     utafitiHapana
    -0.67
    ]--;
    -0.65
     المعيارى
    -0.65
    POSITIVE LOGITS
     cal
    0.68
     Cal
    0.57
    IVEREF
    0.55
     CAL
    0.54
    Cal
    0.54
    cal
    0.53
     Callahan
    0.53
     Cali
    0.50
    CAL
    0.49
    uhi
    0.48
    Activations Density 1.519%

    No Known Activations