© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14867
    Prev
    Next
    INDEX
    Explanations

    technical words related to different fields

    oai_token-act-pair · gemini-2.0-flash

    Science and technology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     unknownFields
    -0.60
     resourceCulture
    -0.60
     "..\..\
    -0.57
    LookAnd
    -0.56
     EClass
    -0.54
    GOTREF
    -0.51
    ]=>
    -0.49
     jadx
    -0.49
    SQLException
    -0.49
    tionnaire
    -0.48
    POSITIVE LOGITS
     ddelweddau
    0.54
    Comfort
    0.48
     kasarigan
    0.45
    ivasan
    0.45
     xrange
    0.44
     nakalista
    0.43
    хіво
    0.43
    endgroup
    0.43
    "',
    0.43
     ویکی‌پدیای
    0.42
    Activations Density 2.763%

    No Known Activations