© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10974
    Prev
    Next
    INDEX
    Explanations

    computer code, error messages, and descriptions of API functions

    oai_token-act-pair · gemini-2.0-flash

    coding-related syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     im
    -0.56
     di
    -0.52
     (
    -0.50
     g
    -0.49
     li
    -0.49
     at
    -0.47
     U
    -0.47
     n
    -0.47
     true
    -0.47
     I
    -0.47
    POSITIVE LOGITS
     Theſe
    1.13
     Efq
    1.11
     wireType
    1.04
    AndEndTag
    1.03
     itſelf
    1.02
     myſelf
    1.02
    saraba
    1.01
    ValueStyle
    1.00
     ſeveral
    0.98
    AccessorTable
    0.97
    Activations Density 3.375%

    No Known Activations