© 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. 4096
    Prev
    Next
    INDEX
    Explanations

    words that indicate research results with statistical significance

    oai_token-act-pair · gemini-2.0-flash

    changes and differences

    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
    significantly
    -1.45
     significantly
    -1.32
    slightly
    -1.20
     considerably
    -1.18
     Slightly
    -1.14
     substantially
    -1.13
    Slightly
    -1.13
     значительно
    -1.09
     Significantly
    -1.05
     slightly
    -1.04
    POSITIVE LOGITS
     im
    0.52
     ten
    0.49
    ahs
    0.49
    новниш
    0.48
    出版年
    0.45
    끼
    0.42
    vdash
    0.41
    lages
    0.40
    ум
    0.40
    etts
    0.39
    Activations Density 2.737%

    No Known Activations