© 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. 2846
    Prev
    Next
    INDEX
    Explanations

    Spanish words, especially those related to news and programming

    oai_token-act-pair · gemini-2.0-flash

    technical programming terms

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

    Non-English text and code

    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
     packageName
    -0.41
    ja
    -0.40
    jud
    -0.39
     videre
    -0.38
    j
    -0.36
    App
    -0.36
    ttino
    -0.36
     App
    -0.35
     j
    -0.34
     né
    -0.34
    POSITIVE LOGITS
    IsContent
    0.83
    \{\\
    0.69
    AxisAlignment
    0.69
     Efq
    0.69
     protoimpl
    0.68
    formik
    0.66
     CHAPITRE
    0.66
     lenker
    0.65
     obé
    0.65
    ArgumentParser
    0.65
    Activations Density 0.543%

    No Known Activations