© 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. 9370
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to leading or hosting a social gathering

    oai_token-act-pair · gemini-2.0-flash

    definitions/etymologies

    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
    tagHelperRunner
    -0.52
     Roskov
    -0.52
    ]]);
    -0.51
    ngdoc
    -0.50
    Enllaces
    -0.50
     mergeFrom
    -0.47
    getActiveSheet
    -0.47
     gått
    -0.46
    igneurs
    -0.45
     posti
    -0.44
    POSITIVE LOGITS
    DoubleQuotes
    0.66
    Personendaten
    0.65
     EconPapers
    0.58
    TestingModule
    0.54
    ParallelGroup
    0.54
    Примечания
    0.54
    AccessorTable
    0.50
    inobu
    0.50
    LEncoder
    0.50
     مشين
    0.50
    Activations Density 2.385%

    No Known Activations