© 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. 3155
    Prev
    Next
    INDEX
    Explanations

    hyphenated numbers, especially those that are related to sports statistics like yards and team rankings

    oai_token-act-pair · gemini-2.0-flash

    -

    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
    انيف
    -0.61
    elemField
    -0.59
      (
    -0.57
     Lira
    -0.56
     window
    -0.52
    MigrationBuilder
    -0.52
     endregion
    -0.52
    hogs
    -0.51
     Wikimedijinoj
    -0.50
     block
    -0.50
    POSITIVE LOGITS
     venons
    0.68
     avoient
    0.65
     financières
    0.60
     auroit
    0.59
     eût
    0.58
     hôtes
    0.57
     cervello
    0.57
     sfera
    0.57
     rapides
    0.57
     debout
    0.57
    Activations Density 2.310%

    No Known Activations