© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3770
    Prev
    Next
    INDEX
    Explanations

    phrases that start with "looking" or are related to searching

    oai_token-act-pair · gemini-2.0-flash

    looking

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     وتسجيلات
    -0.54
     cherchés
    -0.53
    tvguidetime
    -0.52
     diinginkan
    -0.52
    :"-"`
    -0.51
     conocemos
    -0.50
     aidant
    -0.50
    msgSender
    -0.49
    wants
    -0.48
    izr
    -0.48
    POSITIVE LOGITS
     to
    1.27
     ivelany
    0.59
    to
    0.54
     progre
    0.50
     propOrder
    0.49
    StoryboardSegue
    0.49
    Beste
    0.49
    ρίου
    0.47
     To
    0.46
    ToArray
    0.46
    Activations Density 1.167%

    No Known Activations