© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3488
    Prev
    Next
    INDEX
    Explanations

    code syntax keywords and symbols

    oai_token-act-pair · gemini-2.0-flash

    programming functions or methods

    np_token-act-pair-logits · gpt-4o-mini

    Java get/set methods

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     uș
    -0.51
    =@"
    -0.44
     taas
    -0.44
     parede
    -0.44
     connais
    -0.43
     trasparente
    -0.43
     câte
    -0.43
     apprécier
    -0.43
     ritrov
    -0.42
    本
    -0.42
    POSITIVE LOGITS
    RegressionTest
    0.87
    帖最后由
    0.82
     الحره
    0.81
    djangoproject
    0.80
     CreateTagHelper
    0.79
    CHREIB
    0.74
    setupUi
    0.73
    fromnode
    0.73
     mergeFrom
    0.73
     كومونز
    0.71
    Activations Density 0.296%

    No Known Activations