© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15094
    Prev
    Next
    INDEX
    Explanations

    references to software versions and compatibility issues

    oai_token-act-pair · gemini-2.0-flash

    unsupported software version

    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
    KommentareTeilen
    -0.48
     Capacity
    -0.45
     capacity
    -0.45
    abras
    -0.45
     r
    -0.44
    Capacity
    -0.43
    ">—
    -0.42
    bus
    -0.42
     Be
    -0.42
     dimentic
    -0.41
    POSITIVE LOGITS
     AssemblyCompany
    0.90
     gynhyrchwyd
    0.72
     المعيارى
    0.67
    uxxxx
    0.66
    WaitGroup
    0.66
    windowFixed
    0.65
    aarrggbb
    0.65
     pinulongan
    0.65
    expandindo
    0.65
     <<<<<<<<<<<<<<
    0.65
    Activations Density 0.484%

    No Known Activations