© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3555
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to dental care

    oai_token-act-pair · gemini-2.0-flash

    dental hygiene

    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
     bezeichneter
    -1.11
    AddTagHelper
    -1.02
    ::_('
    -0.85
     विश्वसनीयता
    -0.84
    contentLoaded
    -0.83
    tagHelperRunner
    -0.82
    })->
    -0.82
    +#+#
    -0.80
    WireFormatLite
    -0.77
    WithMany
    -0.77
    POSITIVE LOGITS
    then
    0.40
     h
    0.40
    /
    0.40
     then
    0.40
     ne
    0.39
     d
    0.38
    ➯
    0.37
     /
    0.37
    ?
    0.35
     oral
    0.35
    Activations Density 0.500%

    No Known Activations