© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9308
    Prev
    Next
    INDEX
    Explanations

    instances of the word "assignment" or the phrase "assigned to."

    oai_token-act-pair · gemini-2.0-flash

    assignments and errors

    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
     assignment
    -2.39
     assigned
    -2.36
     Assignment
    -2.31
     assign
    -2.31
     ASSIGN
    -2.20
     allocated
    -2.17
     assignments
    -2.17
     assigning
    -2.16
     Assign
    -2.14
     Assigned
    -2.14
    POSITIVE LOGITS
    principalColumn
    0.59
     zu
    0.52
    oredCriteria
    0.51
    TProtocol
    0.51
    Zd
    0.51
    
    0.50
    berdayakan
    0.47
    lucene
    0.46
    Corpus
    0.46
    ंदीखरीदारी
    0.45
    Activations Density 1.845%

    No Known Activations