© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11215
    Prev
    Next
    INDEX
    Explanations

    text related to basketball

    oai_token-act-pair · gemini-2.0-flash

    basketball

    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
    cyklopedia
    -0.57
     boxes
    -0.51
    edipus
    -0.49
    lata
    -0.48
     box
    -0.48
    ):}
    -0.47
     Boxes
    -0.47
     στιγ
    -0.46
    RegressionTest
    -0.46
     saloon
    -0.46
    POSITIVE LOGITS
    posedge
    0.82
    expandindo
    0.72
    CloseOperation
    0.62
     HasFactory
    0.60
    WaitGroup
    0.57
    HandlerContext
    0.57
     Roskov
    0.57
     drives
    0.55
    ">//
    0.54
    igshid
    0.54
    Activations Density 0.335%

    No Known Activations