© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10288
    Prev
    Next
    INDEX
    Explanations

    terms related to medicines, drugs, diseases, side effects and the FDA

    oai_token-act-pair · gemini-2.0-flash

    market authorization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     مشين
    -0.82
     виправивши
    -0.80
    GEBURTS
    -0.63
    ScopeManager
    -0.63
     Exacts
    -0.63
    はじめに
    -0.60
     linkovi
    -0.59
     jsPsych
    -0.57
    клопе
    -0.57
     gue
    -0.57
    POSITIVE LOGITS
     ioutil
    0.51
    tagHelperRunner
    0.47
    getDrawable
    0.44
    jor
    0.43
     '\\;'
    0.42
    Vain
    0.42
    JOR
    0.42
    ه‌اند
    0.41
    Endor
    0.41
    AppMethodBeat
    0.41
    Activations Density 1.079%

    No Known Activations