© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15347
    Prev
    Next
    INDEX
    Explanations

    various common words that frequently appear in dialog or narration, but not strongly consistently

    oai_token-act-pair · gemini-2.0-flash

    come

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     <<<<<<<<<<<<<<
    -0.61
    RenderAtEndOf
    -0.59
    Obrázky
    -0.58
    بوابة
    -0.57
    Архівовано
    -0.57
     getItemCount
    -0.57
    Atsauces
    -0.56
    DispatchToProps
    -0.56
     AssemblyProduct
    -0.56
     difp
    -0.55
    POSITIVE LOGITS
     come
    2.63
     comes
    2.34
     coming
    2.30
     Come
    2.22
    Come
    2.20
    come
    2.20
     COME
    2.17
     came
    2.14
    comes
    2.00
    coming
    2.00
    Activations Density 2.149%

    No Known Activations