© 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. 4702
    Prev
    Next
    INDEX
    Explanations

    German language snippets

    oai_token-act-pair · 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
    TagMode
    -0.75
     InputDecoration
    -0.68
    ViewFeatures
    -0.66
     Normdatei
    -0.65
     GenerationType
    -0.64
     rospy
    -0.63
    InitVars
    -0.63
     mergeFrom
    -0.63
     '\\;'
    -0.61
     BoxDecoration
    -0.60
    POSITIVE LOGITS
    wies
    0.57
     wes
    0.54
     hod
    0.52
     ses
    0.52
    jel
    0.52
     Zie
    0.52
     kla
    0.50
    hos
    0.49
     añ
    0.49
    ilst
    0.48
    Activations Density 0.941%

    No Known Activations