© 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. 5681
    Prev
    Next
    INDEX
    Explanations

    words, especially verbs, related to destruction or forceful separation

    oai_token-act-pair · gemini-2.0-flash

    Something being destroyed

    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
     destruction
    -1.44
     Destruction
    -1.38
     breaking
    -1.35
     broken
    -1.33
     destroyed
    -1.32
    Destruction
    -1.31
     breakage
    -1.28
     Destroy
    -1.28
     destroy
    -1.27
    destruction
    -1.27
    POSITIVE LOGITS
    <bos>
    0.52
    vacy
    0.40
    vances
    0.38
     Kalt
    0.37
    setConfig
    0.37
    InputBorder
    0.37
    cipar
    0.37
    ])));
    0.36
     Dorf
    0.36
     otomatig
    0.36
    Activations Density 1.241%

    No Known Activations