© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3403
    Prev
    Next
    INDEX
    Explanations

    code syntax

    oai_token-act-pair · gemini-2.0-flash

    non-English tokens

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

    source code coordinates

    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
     bet
    -0.52
     "..\..\
    -0.47
    nard
    -0.44
     Wicidata
    -0.43
     bev
    -0.43
     test
    -0.42
    пя
    -0.41
    lasi
    -0.41
     trong
    -0.41
     Bet
    -0.40
    POSITIVE LOGITS
    dyž
    0.72
    posedge
    0.69
     متعلقه
    0.68
    下载附件
    0.68
    تقاوى
    0.62
    HasMaxLength
    0.61
    RegressionTest
    0.60
    سطس
    0.59
    StoreMessageInfo
    0.58
     Wre
    0.58
    Activations Density 9.998%

    No Known Activations