© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14393
    Prev
    Next
    INDEX
    Explanations

    direct quotes or reports of people speaking

    oai_token-act-pair · gemini-2.0-flash

    says

    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
    脚注の使い方
    -0.48
     المعيارى
    -0.47
    SequentialGroup
    -0.47
    افی
    -0.46
     Morty
    -0.45
     beginnetje
    -0.45
     lenker
    -0.45
     numé
    -0.44
    กัน
    -0.43
     Tail
    -0.43
    POSITIVE LOGITS
    said
    0.82
     said
    0.81
     Dijo
    0.78
     saith
    0.72
    <bos>
    0.70
     typelib
    0.69
     SAID
    0.68
    :][
    0.67
     ARB
    0.65
    resaid
    0.65
    Activations Density 0.958%

    No Known Activations