© 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. 3288
    Prev
    Next
    INDEX
    Explanations

    academic biographies and research interests

    oai_token-act-pair · gemini-2.0-flash

    history/culture

    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
     GenerationType
    -0.61
    lorette
    -0.56
    исленность
    -0.54
     quiche
    -0.52
     Voilà
    -0.52
     Faker
    -0.52
     محفوظة
    -0.52
    bux
    -0.51
     rospy
    -0.50
    MessageTagHelper
    -0.50
    POSITIVE LOGITS
    LookAnd
    0.66
    र्भ
    0.61
    addCriterion
    0.60
    DeleteBehavior
    0.60
     protoimpl
    0.59
     autorytatywna
    0.54
    IndentedString
    0.54
    StructEnd
    0.52
     Sy
    0.49
     compétence
    0.49
    Activations Density 16.967%

    No Known Activations