© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3770
    Prev
    Next
    INDEX
    Explanations

    language related to customer service for appliances or other equipment

    oai_token-act-pair · gemini-2.0-flash

    Trucks and vans

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    CrossRef
    -0.68
     Ull
    -0.47
    UIControlState
    -0.47
     Fights
    -0.46
    abbaye
    -0.46
    :+:
    -0.45
    ρασ
    -0.45
     remont
    -0.44
    liffe
    -0.44
     chua
    -0.44
    POSITIVE LOGITS
     vans
    0.81
     trucks
    0.73
     Normdatei
    0.72
     truck
    0.72
     van
    0.69
    SourceChecksum
    0.68
     workers
    0.65
     workman
    0.64
     vehicles
    0.63
    Coordonnées
    0.62
    Activations Density 0.754%

    No Known Activations