© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5122
    Prev
    Next
    INDEX
    Explanations

    end of sentences that start mid-paragraph

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
     Chriftian
    -0.72
     Shakspeare
    -0.69
     feminina
    -0.68
     Cæsar
    -0.65
     Assyrian
    -0.63
     ་་
    -0.61
     fubject
    -0.60
     IFT
    -0.60
     chrétien
    -0.60
     ftate
    -0.59
    POSITIVE LOGITS
     Read
    0.78
     Click
    0.78
     Find
    0.71
     CLICK
    0.71
     click
    0.70
    devamını
    0.69
     Visit
    0.68
     Source
    0.66
     Learn
    0.65
     pic
    0.65
    Activations Density 6.454%

    No Known Activations