© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14950
    Prev
    Next
    INDEX
    Explanations

    words related to application software and software access

    oai_token-act-pair · gemini-2.0-flash

    terms related to mobile applications

    np_token-act-pair-logits · gpt-4o-mini

    mobile apps

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    rungsseite
    -0.68
    bewerken
    -0.57
     دیکھیے
    -0.54
     utafitiHapana
    -0.49
     sqlalchemy
    -0.49
     decorazione
    -0.48
     jspb
    -0.46
    ysław
    -0.45
    зулта
    -0.45
     تضيفلها
    -0.44
    POSITIVE LOGITS
     mobile
    2.06
     app
    1.86
     Mobile
    1.78
     smartphone
    1.77
    mobile
    1.74
     iOS
    1.69
    Mobile
    1.68
     mobiles
    1.68
     App
    1.66
     MOBILE
    1.63
    Activations Density 3.347%

    No Known Activations