© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12801
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to actions being performed or completed.

    oai_token-act-pair · gemini-2.0-flash

    done

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     done
    -2.42
    done
    -2.09
     Done
    -2.00
    Done
    -1.97
     DONE
    -1.78
    DONE
    -1.54
    <bos>
    -1.27
    isDone
    -0.86
     doing
    -0.81
     gjort
    -0.77
    POSITIVE LOGITS
    Према
    0.77
    Архівовано
    0.58
    replyreport
    0.57
     كومونز
    0.57
    adă
    0.57
    inherits
    0.56
     découvrez
    0.56
     FOS
    0.54
     purpoſe
    0.54
    Citiți
    0.53
    Activations Density 3.260%

    No Known Activations