© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12242
    Prev
    Next
    INDEX
    Explanations

    C++ code

    oai_token-act-pair · gemini-2.0-flash

    begin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     whoſe
    -0.78
     Theſe
    -0.75
     kaynağından
    -0.71
     ſeveral
    -0.69
     Efq
    -0.68
     Cæsar
    -0.67
     Anſ
    -0.67
     kasarigan
    -0.65
    __(/*!
    -0.64
     becauſe
    -0.63
    POSITIVE LOGITS
    出版年
    0.66
    findpost
    0.60
    MigrationBuilder
    0.57
    وظ
    0.55
    ylvania
    0.51
    adaptiveStyles
    0.49
    OGND
    0.49
    ValueGeneration
    0.47
    udh
    0.46
     Roskov
    0.45
    Activations Density 21.819%

    No Known Activations