© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7753
    Prev
    Next
    INDEX
    Explanations

    words related to legal and official documents, authorizations, and processes

    oai_token-act-pair · gemini-2.0-flash

    should

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    Must
    -1.64
     Must
    -1.59
    must
    -1.56
     must
    -1.48
    MUST
    -1.31
     MUST
    -1.20
     måste
    -1.04
    必须
    -0.93
     muss
    -0.90
     musia
    -0.90
    POSITIVE LOGITS
     should
    1.51
    Should
    1.29
    should
    1.29
     Should
    1.24
     SHOULD
    0.93
    hould
    0.92
     sollte
    0.85
    应该
    0.84
     sollten
    0.82
     fhould
    0.80
    Activations Density 10.306%

    No Known Activations