© 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. 2418
    Prev
    Next
    INDEX
    Explanations

    sections of the US code or other legal language.

    oai_token-act-pair · gemini-2.0-flash

    technical programming terms

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

    legal 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
    CloseOperation
    -0.59
     setuptools
    -0.59
    EndContext
    -0.54
     lisäksi
    -0.52
    basicConfig
    -0.51
    marshaller
    -0.50
    Odkazy
    -0.50
    PerPage
    -0.49
     giusti
    -0.48
    schild
    -0.48
    POSITIVE LOGITS
    Sprintf
    0.59
    vaadin
    0.53
    Etimología
    0.52
    ()]);
    0.51
     Wicidata
    0.51
    DBNull
    0.50
    "])){
    0.49
    ])]
    0.49
    ]))
    0.49
    DataContract
    0.49
    Activations Density 4.296%

    No Known Activations