© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16012
    Prev
    Next
    INDEX
    Explanations

    a variety of words without any clear connection

    oai_token-act-pair · gemini-2.0-flash

    the word "worth"

    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
     pick
    -0.67
    itanya
    -0.53
    المصدر
    -0.53
    pick
    -0.52
     comp
    -0.52
     note
    -0.52
    DispatchToProps
    -0.51
     Hentet
    -0.51
    áneas
    -0.50
    chọn
    -0.50
    POSITIVE LOGITS
     चीज़ों
    0.62
     Италијани
    0.61
     protoimpl
    0.59
    unknownFields
    0.58
    DockStyle
    0.57
     sing
    0.56
    httphttps
    0.54
    كويكب
    0.53
    adpleegd
    0.53
    twimg
    0.53
    Activations Density 6.100%

    No Known Activations