© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 4902
    Prev
    Next
    INDEX
    Explanations

    pronouns and articles, especially those preceding numbers or dates

    oai_token-act-pair · gemini-2.0-flash

    left

    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
     leaving
    -0.79
    leave
    -0.71
    leaving
    -0.69
    Leave
    -0.69
    Leaving
    -0.65
     Leaving
    -0.63
     leave
    -0.62
    adpleegd
    -0.58
     replaced
    -0.57
     дописавши
    -0.57
    POSITIVE LOGITS
     left
    2.91
     Left
    2.38
    left
    2.31
    Left
    2.23
     LEFT
    2.22
    LEFT
    1.91
    左
    1.69
     izquierda
    1.53
     lef
    1.44
     左
    1.41
    Activations Density 10.581%

    No Known Activations