© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11329
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating a problem, requirement, or condition that needs to be addressed.

    oai_token-act-pair · gemini-2.0-flash

    Business and technical descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     will
    -1.21
    will
    -1.16
     akan
    -1.11
    Will
    -1.10
     sẽ
    -1.09
     Will
    -1.04
     would
    -0.93
    WILL
    -0.93
     WILL
    -0.92
    would
    -0.92
    POSITIVE LOGITS
     AssemblyTitle
    0.66
     is
    0.65
     does
    0.63
     are
    0.62
     gets
    0.60
     fails
    0.56
     makes
    0.55
     obtains
    0.53
     becomes
    0.52
     reaches
    0.52
    Activations Density 3.324%

    No Known Activations