© 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. 4315
    Prev
    Next
    INDEX
    Explanations

    modern electronic devices, and especially smartphones.

    oai_token-act-pair · gemini-2.0-flash

    mobile phones

    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
    JspWriter
    -0.60
    {}{}
    -0.58
    cookieParser
    -0.57
    WireFormat
    -0.56
     CPL
    -0.54
     الحره
    -0.54
    matchCondition
    -0.54
    ATURA
    -0.53
     RequestMethod
    -0.53
     desktops
    -0.53
    POSITIVE LOGITS
     phones
    0.95
     phone
    0.95
    phones
    0.91
     Phone
    0.89
    phone
    0.85
    Phone
    0.84
     smartphone
    0.82
     Phones
    0.82
     iPhone
    0.80
     PHONE
    0.80
    Activations Density 1.070%

    No Known Activations