© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8395
    Prev
    Next
    INDEX
    Explanations

    the word "drive" or "drives" often in the context of vehicles

    oai_token-act-pair · gemini-2.0-flash

    drive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    도
    -0.67
     public
    -0.62
     subject
    -0.60
    hase
    -0.59
     report
    -0.59
    …
    -0.57
     right
    -0.56
    실
    -0.55
     fore
    -0.55
     list
    -0.54
    POSITIVE LOGITS
     <=",
    1.28
    OGND
    1.24
    TypedDataSet
    1.20
    uxxxx
    1.20
    yntaxException
    1.20
     незавершена
    1.19
     Meksiku
    1.18
    PerformLayout
    1.16
     Roskov
    1.15
    ьаж
    1.13
    Activations Density 1.327%

    No Known Activations