© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15044
    Prev
    Next
    INDEX
    Explanations

    words and numbers related to computer models and academic publications describing them

    oai_token-act-pair · gemini-2.0-flash

    models

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     Model
    -1.87
     model
    -1.84
    model
    -1.82
    Model
    -1.77
     models
    -1.76
     MODEL
    -1.73
     Models
    -1.69
    MODEL
    -1.66
     모델
    -1.58
     modèle
    -1.57
    POSITIVE LOGITS
     transférez
    0.52
    assioned
    0.46
    interopRequire
    0.45
    новниш
    0.43
     gang
    0.42
    KEYCODE
    0.40
    energia
    0.40
    Grou
    0.40
     bond
    0.39
     pel
    0.38
    Activations Density 39.654%

    No Known Activations