© 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. 13953
    Prev
    Next
    INDEX
    Explanations

    words and phrases acting as supporting articles or common language.

    oai_token-act-pair · gemini-2.0-flash

    positive adjectives

    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
     betweenstory
    -0.61
     quoting
    -0.58
     playing
    -0.54
     combining
    -0.54
    importante
    -0.53
     averaging
    -0.52
    playing
    -0.51
    couvrez
    -0.51
     hosting
    -0.50
     portraying
    -0.50
    POSITIVE LOGITS
     striking
    1.05
     engaging
    1.04
     satisfying
    0.97
     inviting
    0.91
     fulfilling
    0.91
     stimulating
    0.90
     appealing
    0.86
     Engaging
    0.85
     empowering
    0.82
     encouraging
    0.81
    Activations Density 7.047%

    No Known Activations