© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7534
    Prev
    Next
    INDEX
    Explanations

    words related to performing some kind of activity

    oai_token-act-pair · gemini-2.0-flash

    videos and media

    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
     video
    -0.61
     vidéo
    -0.54
    Video
    -0.52
    "]}
    -0.51
     Video
    -0.50
     wideo
    -0.50
    video
    -0.50
     VIDEO
    -0.49
    rinth
    -0.48
     )}
    -0.47
    POSITIVE LOGITS
    tvguidetime
    0.76
     EconPapers
    0.69
     AssemblyCulture
    0.68
     disambiguazione
    0.65
     InputDecoration
    0.65
    FailureListener
    0.64
     doInBackground
    0.63
    ="@+
    0.61
    solete
    0.59
     astore
    0.59
    Activations Density 3.626%

    No Known Activations