© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10250
    Prev
    Next
    INDEX
    Explanations

    C++ code related to testing tuples and hash values

    oai_token-act-pair · gemini-2.0-flash

    computer code and citations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     IFT
    -0.51
     iq
    -0.51
     ERS
    -0.50
     Iq
    -0.49
     IES
    -0.48
     LDA
    -0.47
     Ith
    -0.47
     INE
    -0.47
     ASE
    -0.46
     Nio
    -0.46
    POSITIVE LOGITS
    unately
    0.67
    eavor
    0.63
    entee
    0.62
    brecht
    0.61
    wollen
    0.61
    ebus
    0.60
    aratus
    0.60
    onnaise
    0.59
    eavour
    0.58
    dorfer
    0.58
    Activations Density 7.197%

    No Known Activations