© 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. 4148
    Prev
    Next
    INDEX
    Explanations

    words related to saliva/oral health

    oai_token-act-pair · gemini-2.0-flash

    chewing

    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
    ]--;
    -0.46
    TestBed
    -0.46
    Aspiration
    -0.45
    LayoutStyle
    -0.45
    mybatisplus
    -0.45
    口
    -0.43
    才
    -0.42
    ]=$
    -0.41
    ENING
    -0.41
     Pap
    -0.40
    POSITIVE LOGITS
     disambiguazione
    0.63
    PerformLayout
    0.60
     auffi
    0.59
     étoit
    0.58
    ิลปะ
    0.57
     jazdy
    0.55
     psychologie
    0.54
     termica
    0.54
     twain
    0.54
     sauvage
    0.53
    Activations Density 26.113%

    No Known Activations