© 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. 7373
    Prev
    Next
    INDEX
    Explanations

    language that describes actions being taken at a higher level

    oai_token-act-pair · gemini-2.0-flash

    steps

    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
    /******/
    -0.50
     Hall
    -0.46
    utnik
    -0.45
     zamanda
    -0.45
    Hall
    -0.45
    hall
    -0.43
    こちらが
    -0.43
     hall
    -0.41
    WindowEvent
    -0.41
     $\
    -0.40
    POSITIVE LOGITS
     myſelf
    1.04
     Theſe
    0.99
     himſelf
    0.97
     Jefus
    0.97
    ſelf
    0.96
    ſelves
    0.95
     Majefty
    0.94
     itſelf
    0.94
     purpoſe
    0.88
     pleaſure
    0.88
    Activations Density 6.187%

    No Known Activations