© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1754
    Prev
    Next
    INDEX
    Explanations

    snippets of online chat

    oai_token-act-pair · gemini-2.0-flash

    French technical discussions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Wikimedijinoj
    -0.68
    AccessorTable
    -0.63
     NavController
    -0.62
    تفصیلات
    -0.59
    Filmografie
    -0.59
     שוליים
    -0.55
     }}"></
    -0.54
    preter
    -0.54
     Giver
    -0.53
     clipper
    -0.53
    POSITIVE LOGITS
    rawDesc
    0.51
    vested
    0.49
     qui
    0.47
    ULATE
    0.46
    activate
    0.46
     men
    0.46
    ouple
    0.45
    zczy
    0.45
    losse
    0.44
     perform
    0.44
    Activations Density 1.607%

    No Known Activations