© 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. 9980
    Prev
    Next
    INDEX
    Explanations

    a variety of seemingly unrelated concepts.

    oai_token-act-pair · gemini-2.0-flash

    technical/research documents

    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
    WindowConstants
    -0.91
     الحره
    -0.89
     disambiguazione
    -0.87
    fjspx
    -0.84
    onViewCreated
    -0.83
     jScrollPane
    -0.80
    Diweddarwch
    -0.79
    httphttps
    -0.73
    adaptiveStyles
    -0.72
    الحياه
    -0.71
    POSITIVE LOGITS
     juſ
    0.47
    structing
    0.47
    et
    0.46
     ſever
    0.46
     bref
    0.46
     ſte
    0.45
    Writable
    0.44
     poffe
    0.44
     ſch
    0.43
     Piso
    0.42
    Activations Density 2.780%

    No Known Activations