© 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. 6094
    Prev
    Next
    INDEX
    Explanations

    a mix of French and English words related to academia, programming, and online chat

    oai_token-act-pair · gemini-2.0-flash

    any mention of institutions or organizations

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

    technical conversation snippets

    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
    ніципа
    -0.68
     Normdatei
    -0.68
    saraba
    -0.64
    findpost
    -0.64
    PropertyChanging
    -0.63
     AssemblyTitle
    -0.63
    UserScript
    -0.63
     nakalista
    -0.63
     jspb
    -0.61
    Hauptartikel
    -0.61
    POSITIVE LOGITS
    ">—
    0.48
    WEBPACK
    0.41
     Дан
    0.41
    栄養
    0.40
    Jäh
    0.39
    aspetto
    0.39
    crops
    0.39
    threaded
    0.38
     Etc
    0.38
     Nähr
    0.37
    Activations Density 0.444%

    No Known Activations