© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6186
    Prev
    Next
    INDEX
    Explanations

    words related to code, math, cars, cooking, royalty, parenting, politics, genealogy

    oai_token-act-pair · gemini-2.0-flash

    actions and states

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    ostante
    -0.66
    ]--;
    -0.64
     NavController
    -0.63
     externi
    -0.63
    UserScript
    -0.63
     désolés
    -0.62
     VizieR
    -0.62
    dafx
    -0.61
    Билгалдахарш
    -0.60
    لينكات
    -0.59
    POSITIVE LOGITS
    tagext
    0.59
     насељу
    0.58
    AlterField
    0.50
    Étape
    0.48
    ăți
    0.46
     any
    0.45
    ])).
    0.45
    marle
    0.45
    GraphicsUnit
    0.44
     each
    0.44
    Activations Density 27.590%

    No Known Activations