© 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. 4633
    Prev
    Next
    INDEX
    Explanations

    legal or employment disclaimers and fine print

    oai_token-act-pair · gemini-2.0-flash

    arrest

    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
     betweenstory
    -0.77
     IT
    -0.75
    fromnode
    -0.70
     AM
    -0.62
    ThroughAttribute
    -0.60
     iNdEx
    -0.59
    SharedCtor
    -0.57
     oprot
    -0.56
    ar
    -0.56
     CIT
    -0.56
    POSITIVE LOGITS
     arrest
    0.70
    Arrest
    0.59
     arrests
    0.56
     arrested
    0.53
     arresting
    0.52
     Infórmanos
    0.51
    TH
    0.50
     prisão
    0.50
    arrest
    0.49
    UP
    0.48
    Activations Density 2.775%

    No Known Activations