© 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. 7848
    Prev
    Next
    INDEX
    Explanations

    articles, prepositions, and words relating to health, risk factors, and app development

    oai_token-act-pair · gemini-2.0-flash

    tokens related to technical terms or code

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

    technical documents

    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
    şiv
    -0.63
     Superhost
    -0.58
     segnale
    -0.57
     zwy
    -0.57
     censiti
    -0.56
    never
    -0.56
    étrie
    -0.56
     varandra
    -0.55
     never
    -0.54
    Vidi
    -0.54
    POSITIVE LOGITS
    ///</
    0.52
    はじめに
    0.47
     springfox
    0.46
    ahy
    0.44
     possibly
    0.44
     Hy
    0.43
    isiaj
    0.43
    脚注の使い方
    0.43
    adaptiveStyles
    0.43
    CloseOperation
    0.42
    Activations Density 0.128%

    No Known Activations