© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5728
    Prev
    Next
    INDEX
    Explanations

    the city of San

    oai_token-act-pair · gemini-2.0-flash

    San

    np_max-act-logits · 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
     NSCoder
    -0.77
     lenker
    -0.73
    EndInit
    -0.73
    WarningLevel
    -0.73
    adaptiveStyles
    -0.70
    Rhestr
    -0.69
     Meksiku
    -0.68
    +#+#
    -0.67
     يتيمه
    -0.67
    PasswordEncoder
    -0.66
    POSITIVE LOGITS
    char
    0.43
     miglia
    0.38
    dem
    0.38
     crossorigin
    0.38
    še
    0.36
     éven
    0.34
    к
    0.34
    Patch
    0.34
    ächlich
    0.34
    шой
    0.34
    Activations Density 0.551%

    No Known Activations