© 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. 7417
    Prev
    Next
    INDEX
    Explanations

    LaTeX syntax for math

    oai_token-act-pair · gemini-2.0-flash

    specific formatting structures in text

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

    }{

    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
    ].)
    -0.57
     Monte
    -0.51
     Vist
    -0.47
    !***
    -0.46
    amsa
    -0.46
    shund
    -0.46
     Debussy
    -0.46
    flashdata
    -0.46
     Susquehanna
    -0.45
     Mozart
    -0.44
    POSITIVE LOGITS
    expandindo
    0.78
     مشين
    0.65
     الحره
    0.60
    Kaynakça
    0.59
     utafitiHapana
    0.58
    脚注の使い方
    0.57
    AnimationsModule
    0.56
    Esperamos
    0.56
    fjspx
    0.53
    (!__
    0.51
    Activations Density 0.214%

    No Known Activations