© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13576
    Prev
    Next
    INDEX
    Explanations

    lines of Java code that declare a new object

    oai_token-act-pair · gemini-2.0-flash

    new

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     bezeichneter
    -0.86
     незавершена
    -0.81
    رشف
    -0.71
     defaultstate
    -0.68
    تفصیلات
    -0.68
    Personensuche
    -0.68
     newOwner
    -0.66
    脚注の使い方
    -0.66
    CGRectMake
    -0.66
     Económica
    -0.66
    POSITIVE LOGITS
    );\
    0.49
    vad
    0.48
    aman
    0.46
    niec
    0.45
    ils
    0.44
    iços
    0.44
    laine
    0.43
    bile
    0.43
    ten
    0.42
    amond
    0.41
    Activations Density 2.236%

    No Known Activations