© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10316
    Prev
    Next
    INDEX
    Explanations

    references to the year 1970 and the 1980s

    oai_token-act-pair · gemini-2.0-flash

    7

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     hypnosis
    -0.50
     Schur
    -0.47
     Lisboa
    -0.47
     tubercle
    -0.46
     superposition
    -0.45
     heresy
    -0.45
     Fremantle
    -0.45
     lepid
    -0.45
     Tripoli
    -0.45
     fuselage
    -0.44
    POSITIVE LOGITS
     pinulongan
    0.88
    0
    0.70
    prnewswire
    0.67
    4
    0.60
    6
    0.59
    9
    0.58
    8
    0.56
     Dec
    0.53
     Engineering
    0.52
    2
    0.51
    Activations Density 20.167%

    No Known Activations