© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4525
    Prev
    Next
    INDEX
    Explanations

    mentions of algorithm(s)

    oai_token-act-pair · gemini-2.0-flash

    algorithm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     Algorithm
    -1.91
     algorithm
    -1.90
     algorithms
    -1.78
     Algorithms
    -1.77
    algorithm
    -1.77
    Algorithm
    -1.75
     algoritmo
    -1.52
     algorit
    -1.45
    algorithms
    -1.41
    GORITHM
    -1.41
    POSITIVE LOGITS
    AndEndTag
    0.53
    манд
    0.45
    cel
    0.45
     Schul
    0.43
    CD
    0.41
    Chham
    0.40
    Al
    0.40
    nh
    0.40
     quiz
    0.39
    inder
    0.39
    Activations Density 0.877%

    No Known Activations