© 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. 12969
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating something exists or the location of something

    oai_token-act-pair · gemini-2.0-flash

    High positions

    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
     <<<<<<<<<<<<<<
    -0.62
    المكان
    -0.57
    ایج
    -0.54
    meral
    -0.54
    MMV
    -0.50
    圳
    -0.48
     himo
    -0.48
    LinkId
    -0.48
    romi
    -0.47
    wę
    -0.46
    POSITIVE LOGITS
     mid
    1.27
     top
    1.22
    mid
    1.08
     middle
    1.05
     high
    1.00
    top
    0.97
     midpoint
    0.95
     upper
    0.93
    Mid
    0.93
     Mid
    0.92
    Activations Density 1.947%

    No Known Activations