© 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. 11590
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to car features and automotive technology

    oai_token-act-pair · gemini-2.0-flash

    Car features

    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
     caminh
    -0.55
    PRNewswire
    -0.53
     acuer
    -0.50
     direta
    -0.50
     doInBackground
    -0.49
     tortas
    -0.48
    tilizer
    -0.47
    ллю
    -0.47
    Aktualisiert
    -0.47
     Gleaner
    -0.47
    POSITIVE LOGITS
    IsContent
    0.69
    лтемелер
    0.63
    SourceChecksum
    0.61
     &___
    0.60
    tache
    0.60
    borderFill
    0.59
    Дереккөздер
    0.59
     /\.(
    0.57
     hefyd
    0.55
    cambio
    0.54
    Activations Density 1.014%

    No Known Activations