© 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. 13046
    Prev
    Next
    INDEX
    Explanations

    words pertaining to mobile device communication over a network

    oai_token-act-pair · gemini-2.0-flash

    connecting

    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
    PMailer
    -0.61
     propOrder
    -0.60
     оригіналу
    -0.56
     חיצוניים
    -0.53
    Autoritní
    -0.52
    GOTREF
    -0.49
    SequentialGroup
    -0.48
    Corpus
    -0.47
    feinander
    -0.46
     Roskov
    -0.45
    POSITIVE LOGITS
     connect
    1.25
     connects
    1.20
     connecting
    1.17
     Connect
    1.16
    Connecting
    1.14
     Connecting
    1.11
    connect
    1.05
    connecting
    1.05
    connects
    1.04
     connected
    0.99
    Activations Density 3.235%

    No Known Activations