© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 16155
    Prev
    Next
    INDEX
    Explanations

    C code related to ARM registers and user modes

    oai_token-act-pair · gemini-2.0-flash

    low level code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     sub
    -0.42
     s
    -0.41
     nhiêu
    -0.39
     trai
    -0.39
     Пред
    -0.39
    byt
    -0.38
    ozof
    -0.38
     sous
    -0.38
    quently
    -0.37
     so
    -0.36
    POSITIVE LOGITS
     متعلقه
    0.98
    Попис
    0.94
     pleaſure
    0.90
    principalTable
    0.83
    featureID
    0.83
    EDEFAULT
    0.82
     purpoſe
    0.82
    دانشنامهٔ
    0.81
     reaſon
    0.79
     neceff
    0.79
    Activations Density 2.584%

    No Known Activations