© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2690
    Prev
    Next
    INDEX
    Explanations

    text about chess, especially chess titles, organizations, and players from Slovenia or Yugoslavia

    oai_token-act-pair · gemini-2.0-flash

    Names and code references

    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
    ]^{\
    -0.50
    emeni
    -0.49
    addContainerGap
    -0.46
    jboss
    -0.46
     [
    -0.46
     ruolo
    -0.45
    ❋
    -0.45
     min
    -0.45
     dig
    -0.45
    }^{\
    -0.45
    POSITIVE LOGITS
     متعلقه
    0.90
     препратки
    0.73
     LoggerFactory
    0.68
    PyExc
    0.68
    omock
    0.67
     upvote
    0.65
    typeorm
    0.64
     ModelExpression
    0.63
     randomization
    0.63
    Географија
    0.63
    Activations Density 37.614%

    No Known Activations