© 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. 15094
    Prev
    Next
    INDEX
    Explanations

    words related to the condition of used merchandise

    oai_token-act-pair · gemini-2.0-flash

    technical descriptions

    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
     new
    -1.73
    new
    -1.63
     nuevas
    -1.30
     nuevos
    -1.29
     nuovi
    -1.28
     nueva
    -1.26
     nuovo
    -1.26
     nouvelles
    -1.26
     nieuwe
    -1.24
     nuevo
    -1.23
    POSITIVE LOGITS
    WireFormatLite
    0.49
     verz
    0.47
     StatelessWidget
    0.47
    sidemargin
    0.46
    OGND
    0.45
    ṳ
    0.44
    GTCX
    0.44
     gynhyrchwyd
    0.44
     meta
    0.44
    
    0.43
    Activations Density 0.511%

    No Known Activations