© 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. 16338
    Prev
    Next
    INDEX
    Explanations

    words referring to time, location, and events

    oai_token-act-pair · gemini-2.0-flash

    Proper

    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
    WireFormatLite
    -0.61
    WEBPACK
    -0.59
    deelte
    -0.56
    onViewCreated
    -0.56
    InjectAttribute
    -0.55
    postmedia
    -0.54
     relevant
    -0.53
    Abitanti
    -0.53
     beginnetje
    -0.53
     Relevant
    -0.53
    POSITIVE LOGITS
    proper
    3.11
     proper
    3.11
     Proper
    2.97
    Proper
    2.84
     PROPER
    2.61
     properly
    2.31
    properly
    2.28
     Properly
    2.02
     improper
    1.51
     Improper
    1.30
    Activations Density 15.677%

    No Known Activations