© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14668
    Prev
    Next
    INDEX
    Explanations

    the word "two" in relation to other options

    oai_token-act-pair · gemini-2.0-flash

    Two

    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
     Efq
    -0.87
     Forumite
    -0.83
     Monfieur
    -0.80
     AssemblyTitle
    -0.79
     kaarangay
    -0.79
     Italijanski
    -0.79
     pleaſure
    -0.76
     Anſ
    -0.75
     itſelf
    -0.75
     RIPRODUZIONE
    -0.75
    POSITIVE LOGITS
    ↵
    0.52
     su
    0.46
     pot
    0.44
    pot
    0.44
     Pot
    0.43
     Old
    0.43
    userdetails
    0.42
     mož
    0.40
     mer
    0.40
     bộ
    0.40
    Activations Density 0.675%

    No Known Activations