© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11555
    Prev
    Next
    INDEX
    Explanations

    dialogue from a comic strip featuring a character named Opal

    oai_token-act-pair · gemini-2.0-flash

    Colon punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     AppBundle
    -0.47
     пун
    -0.45
     Kam
    -0.44
    yorsunuz
    -0.44
    NodeId
    -0.43
     versões
    -0.43
    dahl
    -0.43
     Roskov
    -0.43
    čeno
    -0.42
    bkz
    -0.41
    POSITIVE LOGITS
     utafitiHapana
    0.80
    VIAF
    0.77
     Theſe
    0.75
     AssemblyTitle
    0.75
    featureID
    0.72
    PhysRev
    0.71
    tanleria
    0.71
    IntoConstraints
    0.70
    ReusableCell
    0.68
    DrawerToggle
    0.67
    Activations Density 0.129%

    No Known Activations