© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7882
    Prev
    Next
    INDEX
    Explanations

    the prefix "Kar"

    oai_token-act-pair · gemini-2.0-flash

    words and terms starting with 'Kar'

    np_token-act-pair-logits · gpt-4o-mini

    Kar/Ker

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     autorytatywna
    -0.59
    EDEFAULT
    -0.58
    RTEE
    -0.58
    oneofs
    -0.57
     NPS
    -0.53
    IBarButtonItem
    -0.52
     харак
    -0.52
    ucar
    -0.51
    Popis
    -0.50
    Skocz
    -0.50
    POSITIVE LOGITS
    ölkerung
    0.58
    PageContext
    0.50
     Opener
    0.48
    athons
    0.47
    MutableLiveData
    0.46
    čem
    0.44
    ácio
    0.44
    copyWith
    0.43
    verarbeitung
    0.43
    CCER
    0.42
    Activations Density 0.144%

    No Known Activations