© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11939
    Prev
    Next
    INDEX
    Explanations

    the prefix "Kyu" or "Kyur" in any word.

    oai_token-act-pair · gemini-2.0-flash

    references to Kyuubi

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

    Ky

    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
    LookAnd
    -0.71
    InvalidProtocol
    -0.63
    Portale
    -0.60
    ChildScrollView
    -0.59
    toHaveBeenCalled
    -0.57
     kaarangay
    -0.57
     ThemeData
    -0.57
    पया
    -0.54
    Referanser
    -0.54
    ArrowToggle
    -0.53
    POSITIVE LOGITS
    afficheront
    0.54
     doGet
    0.51
    ObjectContext
    0.46
    newtheorem
    0.45
    ;"></
    0.44
    lesi
    0.43
    まりました
    0.43
    nyataan
    0.42
     möjligt
    0.41
    lastIndexOf
    0.40
    Activations Density 0.331%

    No Known Activations