© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13161
    Prev
    Next
    INDEX
    Explanations

    words related to fine particulates in the air

    oai_token-act-pair · gemini-2.0-flash

    dust

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     dust
    -2.27
    dust
    -1.80
     Dust
    -1.79
    Dust
    -1.61
     DUST
    -1.38
     dusting
    -1.25
     dusted
    -1.25
     polvo
    -1.10
     poussière
    -0.95
     dusty
    -0.94
    POSITIVE LOGITS
    ագրություններ
    0.90
    UpInside
    0.84
    libft
    0.82
    ValueStyle
    0.81
    #+#
    0.78
     tartalomajánló
    0.77
    oa̍t
    0.77
    IsContent
    0.77
     createState
    0.76
     дописавши
    0.75
    Activations Density 2.517%

    No Known Activations