© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7990
    Prev
    Next
    INDEX
    Explanations

    self-referential statements expressing opinion within technical documents

    oai_token-act-pair · gemini-2.0-flash

    think, mind, thought

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     Efq
    -0.85
    setVerticalGroup
    -0.84
     оригіналу
    -0.81
    AnchorStyles
    -0.78
    OGND
    -0.78
     Monfieur
    -0.77
    EDEFAULT
    -0.72
    
    -0.71
     Jefus
    -0.71
     whoſe
    -0.71
    POSITIVE LOGITS
     think
    1.02
    Think
    1.02
     mind
    1.02
     Think
    0.99
     thought
    0.94
    think
    0.94
    mind
    0.90
     thoughts
    0.89
    Mind
    0.88
     Mind
    0.85
    Activations Density 0.804%

    No Known Activations