© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4322
    Prev
    Next
    INDEX
    Explanations

    words and short phrases that express strong opinions or emotions, or introduce dialogue

    oai_token-act-pair · gemini-2.0-flash

    strong opinions being voiced

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     otomatig
    -0.68
     OMITBAD
    -0.66
     propOrder
    -0.66
    ArrowToggle
    -0.62
    addPreferredGap
    -0.59
    AppMethodBeat
    -0.59
    NameInMap
    -0.58
     getItemCount
    -0.58
    __":
    -0.56
     Normdatei
    -0.55
    POSITIVE LOGITS
    BASELINE
    0.69
     satel
    0.52
     accompli
    0.51
     tutt
    0.50
    ItemBackground
    0.49
    ILIA
    0.49
    elen
    0.47
    argument
    0.47
     crow
    0.46
    StructEnd
    0.46
    Activations Density 29.240%

    No Known Activations