© 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. 4708
    Prev
    Next
    INDEX
    Explanations

    words related to code and file paths

    oai_token-act-pair · gemini-2.0-flash

    code, files, and modules

    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
     a
    -0.85
     to
    -0.77
     in
    -0.75
     no
    -0.75
     
    -0.70
     o
    -0.69
     on
    -0.69
     the
    -0.67
     as
    -0.67
     "
    -0.66
    POSITIVE LOGITS
     myſelf
    1.55
     Efq
    1.52
     doubtnut
    1.50
     itſelf
    1.47
     Jefus
    1.43
    ſelves
    1.41
    ſelf
    1.41
     Theſe
    1.37
     Houſe
    1.35
     ―――――
    1.34
    Activations Density 2.228%

    No Known Activations