© 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. 12146
    Prev
    Next
    INDEX
    Explanations

    geographic locations and directional words

    oai_token-act-pair · gemini-2.0-flash

    directions

    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
    WireFormatLite
    -0.69
    photobucket
    -0.63
    出版年
    -0.62
    KommentareTeilen
    -0.60
     lenker
    -0.59
     Riproduzione
    -0.58
    LookAnd
    -0.55
     Efq
    -0.54
     Normdatei
    -0.54
    
    -0.53
    POSITIVE LOGITS
     cheia
    0.53
    ToScroll
    0.51
     pů
    0.48
    writeTo
    0.48
    GenerationType
    0.47
     evolução
    0.47
     cheio
    0.46
     externi
    0.46
    ESI
    0.46
    lossians
    0.45
    Activations Density 1.152%

    No Known Activations