© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12876
    Prev
    Next
    INDEX
    Explanations

    words relating to using buttons/touchscreens on electronic devices

    oai_token-act-pair · gemini-2.0-flash

    Buttons and touch input

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     ImportError
    -0.53
    PyErr
    -0.50
    hatta
    -0.46
     estrategia
    -0.46
    filé
    -0.45
    läufe
    -0.44
    sina
    -0.43
     estratégia
    -0.43
     실
    -0.41
    essai
    -0.41
    POSITIVE LOGITS
    Vidite
    0.73
    الحياه
    0.72
    RenderAtEndOf
    0.69
    GEBURTSDATUM
    0.68
    setVerticalGroup
    0.68
    ManagedBean
    0.68
    findpost
    0.67
    UpInside
    0.66
     pleaſure
    0.66
     Infórmanos
    0.64
    Activations Density 0.618%

    No Known Activations