© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3924
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to installation or repair of vehicle electrical components

    oai_token-act-pair · gemini-2.0-flash

    Electricity/wiring context

    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
     sonno
    -0.60
     montaje
    -0.57
    adaptiveStyles
    -0.55
    Hentet
    -0.55
     صوتيه
    -0.52
     Pingback
    -0.52
     tavo
    -0.51
    لاعات
    -0.50
     quæ
    -0.49
     trajets
    -0.49
    POSITIVE LOGITS
    protoimpl
    0.84
     vulgares
    0.55
     "..\..\
    0.55
    Autoritní
    0.55
    StructEnd
    0.53
    piac
    0.52
     MainAxisSize
    0.50
     Exactos
    0.49
     terminal
    0.49
    rungsseite
    0.48
    Activations Density 3.441%

    No Known Activations